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

    Neuronpedia

    APICircuit 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. 5993
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and material properties

    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
     early
    -0.57
     Early
    -0.46
     office
    -0.44
     mata
    -0.43
    íticas
    -0.41
    cita
    -0.41
    Early
    -0.41
    êche
    -0.40
     late
    -0.40
    alpin
    -0.40
    POSITIVE LOGITS
    expandindo
    0.92
    Personendaten
    0.86
    Morfologia
    0.85
    Tikang
    0.80
    RectangleBorder
    0.78
     BoxDecoration
    0.76
    HtmlAttribute
    0.74
    IntoConstraints
    0.74
    qrstuvwxyz
    0.71
    AutoScaleMode
    0.70
    Activations Density 1.843%

    No Known Activations