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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7821
    Prev
    Next
    INDEX
    Explanations

    phrases related to tax issues and corporate governance

    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
     enfans
    -0.43
    ziasztok
    -0.35
     avoient
    -0.33
    ſelf
    -0.31
     babi
    -0.30
    futter
    -0.30
    BagLayout
    -0.29
     gravidez
    -0.29
     Lengkap
    -0.28
     étoit
    -0.28
    POSITIVE LOGITS
    CppCodeGen
    0.64
     HttpNotFound
    0.60
    нгред
    0.57
     utafitiHapana
    0.57
    SharedCtor
    0.56
    ariConfig
    0.56
     surla
    0.55
    bootstrapcdn
    0.55
     unknownFields
    0.55
     CanadaChoose
    0.54
    Activations Density 0.229%

    No Known Activations