© 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. 28-GEMMASCOPE-RES-16K
    11. 3367
    Prev
    Next
    INDEX
    Explanations

    references to scientific concepts and technical descriptions

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

    Followed by a form of "to be."

    np_acts-logits-general · gemini-2.0-flash

    are noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.44
    atorul
    -0.44
    engesch
    -0.42
    RTEE
    -0.42
    mery
    -0.42
    itoare
    -0.42
     Moscú
    -0.41
    StructEnd
    -0.41
     Şi
    -0.41
     îna
    -0.41
    POSITIVE LOGITS
     are
    0.67
     themselves
    0.61
     eivät
    0.56
     were
    0.55
     jsou
    0.55
     ſind
    0.54
     mają
    0.54
     själva
    0.53
    themselves
    0.53
     których
    0.52
    Activations Density 0.591%

    No Known Activations