© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12676
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships

    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
    ]--;
    -0.71
    Hochspringen
    -0.67
     Meksiku
    -0.60
    zzleHttp
    -0.57
     kasarigan
    -0.56
     Hend
    -0.56
     ***!
    -0.56
    Халык
    -0.55
    Билгалдахарш
    -0.55
     rând
    -0.55
    POSITIVE LOGITS
     onCreateView
    0.61
     puto
    0.61
    HasColumnType
    0.59
     chrétienne
    0.53
    Parms
    0.52
    lorette
    0.52
     InputDecoration
    0.52
     Soli
    0.52
     schuld
    0.51
    DoubleQuotes
    0.51
    Activations Density 0.431%

    No Known Activations