© 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. 4-GEMMASCOPE-RES-16K
    6. 12739
    Prev
    Next
    INDEX
    Explanations

    terms related to 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 @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.82
     cister
    -0.79
    tagext
    -0.79
    <?,
    -0.77
    المصدر
    -0.76
     Ceinture
    -0.76
    SessionFactory
    -0.74
    irchen
    -0.73
     сде
    -0.72
     Erskine
    -0.72
    POSITIVE LOGITS
     ALLOW
    1.84
     allowed
    1.84
    ALLOW
    1.84
     allow
    1.83
     Allow
    1.78
     allows
    1.71
    Allow
    1.70
     Allows
    1.67
    allow
    1.65
     Allowed
    1.61
    Activations Density 0.076%

    No Known Activations