© 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. 0-GEMMASCOPE-RES-16K
    11. 7257
    Prev
    Next
    INDEX
    Explanations

    terms related to granting permission or enabling actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeneratedMessage
    -0.63
    يميديا
    -0.62
    Références
    -0.61
    getDoctrine
    -0.57
     Bourgoin
    -0.55
    ClCompile
    -0.53
    PRNewswire
    -0.53
    Marshall
    -0.52
     Ressources
    -0.52
     références
    -0.52
    POSITIVE LOGITS
    allow
    2.03
     permit
    1.98
     allow
    1.96
     Allow
    1.95
    Allow
    1.95
     ALLOW
    1.84
     Permit
    1.83
     permits
    1.83
    ALLOW
    1.81
     allowed
    1.80
    Activations Density 0.282%

    No Known Activations