© 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. 1119
    Prev
    Next
    INDEX
    Explanations

    references to testimonies and statements related to historical contexts and individuals

    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
     comportements
    -0.85
     behavioural
    -0.83
     vectorielles
    -0.80
     télévis
    -0.77
     traditionnelle
    -0.76
     Verhaltens
    -0.75
    behaviour
    -0.75
     Behavioural
    -0.74
     juridiques
    -0.74
     comportement
    -0.72
    POSITIVE LOGITS
    GeneratedMessage
    0.56
    MethodManager
    0.56
    HideFlags
    0.53
     arşivlendi
    0.52
     aud
    0.49
     Terre
    0.49
    erialized
    0.48
    Tikang
    0.47
    Geo
    0.47
     Respectfully
    0.46
    Activations Density 0.737%

    No Known Activations