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. 2-GEMMASCOPE-RES-16K
    6. 6788
    Prev
    Next
    INDEX
    Explanations

    references to actions and references, particularly those pertaining to performance or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ்கள்
    -0.97
    GEBURTSDATUM
    -0.94
    ="<?=$
    -0.86
    ikation
    -0.86
    IDATE
    -0.83
    <?=$
    -0.82
    lampe
    -0.81
     holt
    -0.80
    mybatisplus
    -0.77
    PerformLayout
    -0.77
    POSITIVE LOGITS
    ed
    1.56
    ized
    0.97
    ated
    0.93
     Interpre
    0.73
     bik
    0.71
     Prow
    0.71
     raiſ
    0.69
    ian
    0.69
     Szw
    0.69
     Pick
    0.69
    Activations Density 0.205%

    No Known Activations