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. 9-GEMMASCOPE-RES-16K
    6. 9348
    Prev
    Next
    INDEX
    Explanations

    sections related to mathematical proofs and theorem statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppBundle
    -1.12
    Hochspringen
    -0.98
    $")
    -0.98
    Tembelea
    -0.94
    IBOutlet
    -0.93
    djangoproject
    -0.90
     Burs
    -0.88
    Xna
    -0.88
    ."]
    -0.88
     يتيمه
    -0.88
    POSITIVE LOGITS
    Proof
    1.25
    proof
    1.18
     Proof
    1.18
     PROOF
    1.15
     proof
    1.08
     proofs
    1.02
    PROOF
    1.01
     Proofs
    0.94
    ed
    0.70
     Pob
    0.70
    Activations Density 0.038%

    No Known Activations