© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 5851
    Prev
    Next
    INDEX
    Explanations

    references to the present or current topics of discussion

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

    the phrase "In this" at the beginning of sentences introducing study descriptions or methodological sections.

    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
    LookAnd
    -0.61
     unknownFields
    -0.59
    AccessorTable
    -0.55
    UrlResolution
    -0.54
     QtWidgets
    -0.54
     Numerade
    -0.53
    SourceChecksum
    -0.52
    CppCodeGen
    -0.51
     pinulongan
    -0.51
     propOrder
    -0.51
    POSITIVE LOGITS
     regard
    0.87
     regards
    0.65
     instance
    0.62
     respect
    0.61
     ocasión
    0.59
     context
    0.56
     reason
    0.56
     manner
    0.54
     sort
    0.54
     case
    0.53
    Activations Density 0.233%

    No Known Activations