© 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. 7-GEMMASCOPE-RES-16K
    11. 9132
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that emphasize a significant difference in quantity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::~
    -0.65
     EdgeInsets
    -0.61
    tuuri
    -0.60
     Clos
    -0.59
     newest
    -0.58
    Clik
    -0.58
    tifkan
    -0.58
     coûte
    -0.58
    addPreferredGap
    -0.57
     oldest
    -0.57
    POSITIVE LOGITS
    раздо
    0.81
     Roskov
    0.69
    TypedDataSet
    0.68
    .*")]
    0.62
     TMPro
    0.61
     wesentlich
    0.60
    榄
    0.59
     *)__
    0.57
     beaucoup
    0.57
     resourceCulture
    0.57
    Activations Density 0.177%

    No Known Activations