© 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. 25-GEMMASCOPE-RES-16K
    11. 250
    Prev
    Next
    INDEX
    Explanations

    modal verbs reflecting necessity or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    giro
    -0.52
     tomorrow
    -0.48
     capacity
    -0.45
    >//
    -0.45
    Rhestr
    -0.43
    piracy
    -0.43
     unqualified
    -0.43
     Antiquity
    -0.42
    oon
    -0.42
     medically
    -0.42
    POSITIVE LOGITS
     war
    0.80
     hatte
    0.78
     waren
    0.78
     kam
    0.77
     ging
    0.77
     gab
    0.75
     konnte
    0.74
     gingen
    0.74
     kamen
    0.74
     hatten
    0.73
    Activations Density 0.046%

    No Known Activations