© 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. 10-GEMMASCOPE-RES-16K
    6. 4352
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the movement or transition into new contexts or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âgées
    -0.78
     Balboa
    -0.74
    GRAPH
    -0.73
     Calvo
    -0.72
     Weh
    -0.72
     AAS
    -0.71
     africains
    -0.70
     Mesozoic
    -0.69
    Busch
    -0.68
     PAH
    -0.68
    POSITIVE LOGITS
     INTO
    1.71
     Into
    1.67
    Into
    1.61
     into
    1.56
    INTO
    1.40
    into
    1.20
     onto
    0.94
    *</
    0.87
    ")){
    
    0.86
    "]).
    0.82
    Activations Density 0.118%

    No Known Activations