© 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. 8358
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal decisions and recommendations

    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
     beginnetje
    -0.97
     myſelf
    -0.85
     whoſe
    -0.82
     pleaſure
    -0.80
     Jefus
    -0.80
     Efq
    -0.79
     Monfieur
    -0.79
     nahilalakip
    -0.78
     Италијани
    -0.77
     raiſ
    -0.76
    POSITIVE LOGITS
     suggest
    1.63
     suggests
    1.49
     suggesting
    1.38
    suggest
    1.37
     hint
    1.35
     suggestion
    1.33
    Hint
    1.31
    hint
    1.22
     hints
    1.21
     Suggest
    1.21
    Activations Density 0.182%

    No Known Activations