© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10055
    Prev
    Next
    INDEX
    Explanations

    terms related to compatibility and configuration settings in various contexts

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    The
    -0.55
     établissements
    -0.51
     língua
    -0.48
    jmniej
    -0.46
    ty
    -0.46
    Fier
    -0.46
    Hints
    -0.46
    kot
    -0.45
    колко
    -0.45
    akim
    -0.45
    POSITIVE LOGITS
     config
    1.00
    Allow
    0.98
     Allow
    0.97
     ALLOW
    0.96
     allow
    0.92
     Config
    0.91
     Allows
    0.90
    Allows
    0.89
     Allowing
    0.88
    allow
    0.88
    Activations Density 0.083%

    No Known Activations