© 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. 14-GEMMASCOPE-RES-16K
    6. 11046
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries seeking clarification or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.83
    Diwedd
    -0.82
     Савезне
    -0.79
     تكبرها
    -0.77
    providedIn
    -0.72
     @}
    -0.69
     виправивши
    -0.68
    SerializedName
    -0.65
    +};
    -0.65
    ImageContext
    -0.65
    POSITIVE LOGITS
     Unido
    0.58
    ↵↵
    0.57
    .
    0.55
    ↵
    0.54
     Dostupné
    0.51
    равда
    0.45
    ...
    0.45
     milioane
    0.44
    ViewFeatures
    0.44
        
    0.43
    Activations Density 0.144%

    No Known Activations