Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15000
    Prev
    Next
    INDEX
    Explanations

    instances of the word "also" as well as terms related to literature and freshwater resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.88
    StoryboardSegue
    -0.85
    ⓧ
    -0.80
    ngdoc
    -0.78
    Xna
    -0.73
    ValueStyle
    -0.72
     Drapeau
    -0.71
    MessageOf
    -0.70
    出版年
    -0.69
     GenerationType
    -0.69
    POSITIVE LOGITS
     literature
    0.71
     Also
    0.65
     noch
    0.64
     banding
    0.59
     Theſe
    0.59
     lineup
    0.58
    Comentários
    0.58
     readings
    0.57
    פרי
    0.56
    Also
    0.56
    Activations Density 0.055%

    No Known Activations