© 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. 6-GEMMASCOPE-RES-16K
    11. 5628
    Prev
    Next
    INDEX
    Explanations

    dates and numerical information relevant to historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poêle
    -0.51
    cellona
    -0.51
     λό
    -0.50
    Mittwoch
    -0.49
    спонд
    -0.48
    ocd
    -0.48
    матика
    -0.48
    nachweis
    -0.48
    genossen
    -0.47
    cyj
    -0.47
    POSITIVE LOGITS
    LookAnd
    1.00
    ########.
    0.98
    PreferredItem
    0.84
    AndEndTag
    0.81
    UIControlState
    0.80
    
    0.78
    帖最后由
    0.78
    Portale
    0.78
    sidemargin
    0.76
    vician
    0.74
    Activations Density 0.223%

    No Known Activations