© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 12952
    Prev
    Next
    INDEX
    Explanations

    technical terms and constructs commonly used in programming or software documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acct
    -0.76
     Resp
    -0.74
     Univ
    -0.73
    Chk
    -0.72
     chk
    -0.72
     Bk
    -0.72
     Req
    -0.71
     req
    -0.71
     eqn
    -0.71
     ppl
    -0.70
    POSITIVE LOGITS
    configuration
    0.75
    CONFIGURATION
    0.74
    Configuration
    0.65
     يتيمه
    0.64
    MAXIMUM
    0.63
     CONFIGURATION
    0.62
    initialization
    0.59
    maximum
    0.59
    specification
    0.59
    configurations
    0.58
    Activations Density 1.164%

    No Known Activations