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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12704
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to explosions and explosives

    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
     Normdatei
    -0.82
    ScopeManager
    -0.66
     AspNetCore
    -0.61
     rând
    -0.59
     Lari
    -0.55
    tslib
    -0.54
     sujets
    -0.53
     toscana
    -0.53
     soin
    -0.53
    ^(
    -0.53
    POSITIVE LOGITS
     explosions
    1.33
     Explosion
    1.32
     explosion
    1.31
     explosives
    1.26
     exploding
    1.20
     explosive
    1.17
     explodes
    1.17
     exploded
    1.17
     blown
    1.17
     Explosive
    1.16
    Activations Density 0.186%

    No Known Activations