Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15411
    Prev
    Next
    INDEX
    Explanations

    terms related to data processing and algorithm function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    siamo
    -0.48
    msgTypes
    -0.47
     >=",
    -0.46
    zoni
    -0.44
    istic
    -0.43
     iconic
    -0.42
     Southern
    -0.42
    ıyorum
    -0.42
     Gene
    -0.41
     grid
    -0.41
    POSITIVE LOGITS
     Chwiliwch
    0.58
     defaultstate
    0.50
    ActionCreators
    0.48
    󠁿
    0.48
    ConstraintMaker
    0.48
    tvguidetime
    0.47
     oprot
    0.46
    mybatisplus
    0.46
    IVEREF
    0.46
    errHandler
    0.44
    Activations Density 1.229%

    No Known Activations