© 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. 8-GEMMASCOPE-RES-16K
    6. 10146
    Prev
    Next
    INDEX
    Explanations

    information related to age, statistics, and specific names in a medical or academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    й
    -1.08
    一个
    -0.94
    Gott
    -0.87
    __*/
    -0.86
     Baldwin
    -0.84
    Barr
    -0.84
     Bartol
    -0.84
    CloseOperation
    -0.84
    йки
    -0.83
    OTT
    -0.80
    POSITIVE LOGITS
    に
    1.01
    ly
    0.95
     Lynd
    0.89
     soeur
    0.84
    ab
    0.83
     Landis
    0.80
     suivie
    0.79
     moeite
    0.79
    gnügen
    0.78
    ag
    0.78
    Activations Density 3.043%

    No Known Activations