© 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. 1-GEMMASCOPE-RES-16K
    11. 7188
    Prev
    Next
    INDEX
    Explanations

    the name "Saddler" in various contexts, especially when it appears in a dramatic or narrative setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     링크
    -0.60
    Voir
    -0.58
    __':
    -0.56
    gendes
    -0.56
    polish
    -0.55
     betweenstory
    -0.55
     beginnetje
    -0.54
     Dube
    -0.53
    rrggbb
    -0.53
    льше
    -0.53
    POSITIVE LOGITS
     explosion
    1.03
     exploded
    0.87
     Explosion
    0.87
     explodes
    0.85
     explode
    0.82
     burst
    0.82
    Tre
    0.82
    explosion
    0.80
    Explosion
    0.78
     explosive
    0.78
    Activations Density 0.057%

    No Known Activations