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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11179
    Prev
    Next
    INDEX
    Explanations

    questions and responses, particularly in the context of requests for help or clarification

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

    Followed by "A:" or "Thanks"

    np_acts-logits-general · gemini-2.0-flash

    greetings and responses

    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
     فريبيس
    -0.63
    AnchorStyles
    -0.58
    addPreferredGap
    -0.56
    principalColumn
    -0.54
    featureID
    -0.53
    ChildScrollView
    -0.50
    sidemargin
    -0.49
    COUVER
    -0.47
     Exactos
    -0.46
     <=",
    -0.46
    POSITIVE LOGITS
    Dear
    0.62
     Hello
    0.61
     Dear
    0.59
    Hello
    0.56
     hello
    0.56
    Hi
    0.51
     hi
    0.50
     Hi
    0.50
     Reply
    0.47
    plz
    0.46
    Activations Density 0.710%

    No Known Activations