© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10751
    Prev
    Next
    INDEX
    Explanations

    references to academic sources, specifically related to Google Scholar or similar citation indexing terms

    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
    DebuggerNonUser
    -0.84
     JScrollPane
    -0.58
    ształ
    -0.57
    Rcpp
    -0.56
    SceneManagement
    -0.56
    ferrer
    -0.53
    quoise
    -0.50
    zens
    -0.50
    carousel
    -0.49
     Flur
    -0.48
    POSITIVE LOGITS
    thenReturn
    1.15
    assertEqual
    1.01
    enumi
    0.93
     ModelExpression
    0.89
     NOI
    0.86
    BeginInit
    0.82
     metav
    0.73
    __":
    0.70
     متعلقه
    0.70
    EndInit
    0.69
    Activations Density 0.039%

    No Known Activations