© 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. 8-GEMMASCOPE-RES-16K
    11. 5717
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the makeup or structure of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципа
    -0.76
     maxn
    -0.76
     SDLK
    -0.70
     techniczne
    -0.69
     cuillère
    -0.68
     Schild
    -0.67
    IsPostBack
    -0.66
    السكان
    -0.65
    icolon
    -0.65
    rdoba
    -0.64
    POSITIVE LOGITS
     compose
    1.71
     composed
    1.70
    composed
    1.63
     Composition
    1.60
     composition
    1.57
     Compose
    1.52
     Composed
    1.52
     compositions
    1.51
     composing
    1.50
    Compos
    1.49
    Activations Density 0.100%

    No Known Activations