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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4540
    Prev
    Next
    INDEX
    Explanations

    questions and requests for feedback or opinions

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

    Question or opinion elicitation

    np_acts-logits-general · gemini-2.0-flash

    asking for opinions or comments

    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
    pushFollow
    -0.58
    WebElementEntity
    -0.51
    IsContent
    -0.51
     Exacts
    -0.49
    GIVEREF
    -0.48
     ویکی‌پدی
    -0.45
     fevere
    -0.44
    BufferException
    -0.44
     ſou
    -0.44
    ThroughAttribute
    -0.43
    POSITIVE LOGITS
     opinion
    1.68
     opinions
    1.53
    opinion
    1.38
     opinión
    1.38
     comment
    1.38
     Opinion
    1.34
     comments
    1.31
     Opinions
    1.29
    Opinion
    1.28
     opin
    1.26
    Activations Density 0.371%

    No Known Activations