© 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. 22-GEMMASCOPE-RES-16K
    6. 10141
    Prev
    Next
    INDEX
    Explanations

    titles of photographic works and exhibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.66
    mybatisplus
    -0.65
    Parcelize
    -0.58
     kaarangay
    -0.57
    SuppressLint
    -0.55
    
    -0.53
     Partagez
    -0.52
    Jeografia
    -0.51
    complexType
    -0.51
    teryx
    -0.51
    POSITIVE LOGITS
     gallery
    1.05
     curator
    0.96
     galleries
    0.93
     cur
    0.88
     exhibition
    0.84
    gallery
    0.82
    curator
    0.81
     Curator
    0.81
     Galleries
    0.80
     Gallery
    0.78
    Activations Density 0.190%

    No Known Activations