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. 12-GEMMASCOPE-RES-16K
    6. 11849
    Prev
    Next
    INDEX
    Explanations

    names and family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.89
    DockStyle
    -0.81
    __*/
    -0.79
     SwitchCompat
    -0.76
    存于互联网档案馆
    -0.75
     kaynağından
    -0.68
    ^(@)
    -0.66
     архивлан
    -0.66
     defaultstate
    -0.65
    TagHelper
    -0.65
    POSITIVE LOGITS
    posit
    0.57
    submitted
    0.47
     who
    0.46
     Fe
    0.43
    POST
    0.43
    passphrase
    0.42
    RunWith
    0.40
     var
    0.40
     ad
    0.40
     Daniel
    0.39
    Activations Density 0.023%

    No Known Activations