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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 13485
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direction or progression toward a conclusion or end

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Calvo
    -0.74
    t
    -0.71
     fatica
    -0.70
    5
    -0.69
     foglal
    -0.67
    T
    -0.65
     печа
    -0.63
     cy
    -0.63
     riuscito
    -0.63
    </em>
    -0.62
    POSITIVE LOGITS
    toward
    2.19
    towards
    2.15
     toward
    2.12
     Towards
    2.11
     Toward
    2.09
    Towards
    2.06
     towards
    2.04
    Toward
    1.93
     hacia
    1.46
     TOW
    1.38
    Activations Density 0.056%

    No Known Activations