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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13945
    Prev
    Next
    INDEX
    Explanations

    references to financial terms and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -1.07
    Personensuche
    -1.01
    ChildScrollView
    -0.98
    MigrationBuilder
    -0.89
     Efq
    -0.89
     الحره
    -0.88
    NewUrlParser
    -0.84
    GraphicsUnit
    -0.84
    󠁴
    -0.83
     незавершена
    -0.82
    POSITIVE LOGITS
     B
    2.22
     A
    2.16
     C
    1.86
    B
    1.84
    A
    1.77
     D
    1.63
    C
    1.49
     E
    1.29
    D
    1.29
     А
    1.27
    Activations Density 1.870%

    No Known Activations