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. 23-GEMMASCOPE-RES-16K
    6. 12556
    Prev
    Next
    INDEX
    Explanations

    elements related to tension and suspense in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -0.85
     poichè
    -0.85
    Whilst
    -0.83
     welche
    -0.83
     didalam
    -0.83
     welches
    -0.81
     می‌باشد
    -0.78
     welcher
    -0.77
    非常的
    -0.76
     diatas
    -0.76
    POSITIVE LOGITS
    ​—
    0.97
    —“
    0.91
    —"
    0.83
     freilich
    0.79
    —
    0.71
    —”
    0.68
     apiece
    0.68
     manqué
    0.67
     persino
    0.67
    --"
    0.66
    Activations Density 2.096%

    No Known Activations