© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4118
    Prev
    Next
    INDEX
    Explanations

    references to specific categories and classifications of data, especially in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    abbreviation patterns, particularly initials with periods such as "F.C." or organizational acronyms like "CC" followed by numbers or letters.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    abbreviations and acronyms, particularly those consisting of capital letters followed by periods or numbers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    چه
    -0.44
    GraphicsUnit
    -0.39
     Einsch
    -0.37
    Jokes
    -0.36
    +#+#
    -0.36
     considérons
    -0.35
    csname
    -0.34
    culated
    -0.34
    ectady
    -0.34
    prom
    -0.34
    POSITIVE LOGITS
    Rhestr
    0.49
    IsMutable
    0.47
    AxisAlignment
    0.47
    tonsoft
    0.47
    ſelf
    0.44
     queſta
    0.44
    GEBURTSDATUM
    0.44
    Rujuakan
    0.43
     समीक्षाओं
    0.43
     estekak
    0.42
    Activations Density 0.441%

    No Known Activations