© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 12718
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and relationships in a formal proof context

    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
     (°
    -0.56
    uelas
    -0.55
     PRIMARY
    -0.55
     kee
    -0.54
     lau
    -0.51
    umat
    -0.51
    wania
    -0.50
     primary
    -0.50
    getSystemService
    -0.50
    Primary
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.66
     noDo
    0.63
     przecież
    0.60
     gedrag
    0.60
    ztály
    0.59
     tartalomajánló
    0.57
     polaire
    0.55
    EndContext
    0.55
     obligado
    0.54
     démo
    0.54
    Activations Density 1.681%

    No Known Activations