© 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. 5-GEMMASCOPE-RES-16K
    11. 10790
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms related to scientific subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.88
    __":
    -0.77
     Kese
    -0.74
    polator
    -0.74
    principalColumn
    -0.71
     дописавши
    -0.71
     vian
    -0.70
    BorderFactory
    -0.69
    matchCondition
    -0.68
    Revenir
    -0.68
    POSITIVE LOGITS
    Portale
    0.97
    iredo
    0.72
    Leeds
    0.63
     Dawkins
    0.63
     karbon
    0.63
     Leeds
    0.60
     Ley
    0.60
     Berliner
    0.59
     Guelph
    0.59
     Urbana
    0.59
    Activations Density 1.294%

    No Known Activations