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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 13158
    Prev
    Next
    INDEX
    Explanations

    references to academic databases and platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cockpit
    -0.59
    fiques
    -0.57
     isos
    -0.56
    WithIOException
    -0.55
    räger
    -0.54
     meson
    -0.53
    flink
    -0.53
     قرب
    -0.52
    存于互联网档案馆
    -0.51
    ⑤
    -0.51
    POSITIVE LOGITS
    jspx
    1.07
    ScopeManager
    1.05
    migrationBuilder
    1.02
    ="../
    0.82
    AnchorStyles
    0.78
    URLException
    0.77
    Linq
    0.76
    amssymb
    0.74
     []:
    0.70
     AppCompatTheme
    0.69
    Activations Density 0.006%

    No Known Activations