© 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. 7-GEMMASCOPE-RES-16K
    11. 1726
    Prev
    Next
    INDEX
    Explanations

    references to causal relationships and inference models in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntö
    -0.56
     sca
    -0.47
     platforms
    -0.47
    mær
    -0.46
    にと
    -0.46
     lạc
    -0.46
     disputed
    -0.46
    glichen
    -0.45
     contest
    -0.45
     disagree
    -0.45
    POSITIVE LOGITS
     causality
    1.06
     causation
    1.04
     Causal
    0.97
     causal
    0.96
    Caus
    0.90
     Caus
    0.85
    cause
    0.85
     cause
    0.83
     Meksiku
    0.80
     Cause
    0.79
    Activations Density 0.914%

    No Known Activations