© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5922
    Prev
    Next
    INDEX
    Explanations

    mentions of performance spaces and stages

    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
     bajas
    -0.53
     őket
    -0.50
     salido
    -0.48
     gustado
    -0.48
     GenerationType
    -0.48
     hark
    -0.45
     bassa
    -0.44
     agences
    -0.44
     variar
    -0.44
    Życiorys
    -0.44
    POSITIVE LOGITS
     podium
    0.99
     onstage
    0.89
     pulpit
    0.87
     doubtnut
    0.79
     stage
    0.79
     screen
    0.78
     Bühnen
    0.78
     shelves
    0.78
     throne
    0.77
     backstage
    0.77
    Activations Density 0.351%

    No Known Activations