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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 2878
    Prev
    Next
    INDEX
    Explanations

    sections and structural components related to research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.64
    </i>
    -0.59
    </u>
    -0.56
    </h4>
    -0.51
    ,
    -0.49
     saites
    -0.46
     właśnie
    -0.46
    .”
    -0.44
     ‌
    -0.44
    </h2>
    -0.43
    POSITIVE LOGITS
     unknownFields
    0.98
    Personensuche
    0.88
     surla
    0.79
     tartalomajánló
    0.77
     GetEnumerator
    0.76
     ujednoznacz
    0.76
    oneofs
    0.73
     виправивши
    0.73
    IntoConstraints
    0.72
     initComponents
    0.72
    Activations Density 1.101%

    No Known Activations