© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6084
    Prev
    Next
    INDEX
    Explanations

    technical references or annotations in code

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

    Code with exception handling

    np_acts-logits-general · gemini-2.0-flash

    block followed by parenthesis or closing tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.64
     Signalez
    -0.63
    invokeLater
    -0.57
    IsMutable
    -0.56
    WebElementEntity
    -0.55
    UrlResolution
    -0.53
    utilisons
    -0.52
     transférez
    -0.51
     ivelany
    -0.50
    +#+#
    -0.49
    POSITIVE LOGITS
    ремя
    0.40
     facturas
    0.38
     gonzález
    0.36
     soát
    0.34
     defStyle
    0.34
     myſelf
    0.34
    ByUsername
    0.33
    RemoteException
    0.33
     sánchez
    0.33
    unknown
    0.33
    Activations Density 0.141%

    No Known Activations