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. 2-GEMMASCOPE-RES-16K
    6. 6179
    Prev
    Next
    INDEX
    Explanations

    sections in the text that contain comment endings or markers from code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.72
    IntoConstraints
    -0.63
    IBarButtonItem
    -0.62
    jMenuItem
    -0.62
    featureID
    -0.61
     isInitialized
    -0.60
    tableFuture
    -0.60
     AssemblyCompany
    -0.60
    zeptember
    -0.56
     HttpNotFound
    -0.55
    POSITIVE LOGITS
    folgt
    0.59
     ]);
    0.57
     defaultstate
    0.57
    $}}
    0.57
    Bakgrunnsstoff
    0.55
    ()])
    0.52
     */,
    0.52
    ":[{
    0.52
    ();*/
    0.50
    "]];
    0.49
    Activations Density 1.392%

    No Known Activations