© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 610
    Prev
    Next
    INDEX
    Explanations

    offers related to free trials and downloads

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to a specific software tool or application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    free trial or demo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }))
    
    -0.54
     Commissioner
    -0.53
     nhiên
    -0.53
     commissioner
    -0.51
    eqn
    -0.51
    (")");
    -0.46
    UPC
    -0.42
     ordin
    -0.42
    èdia
    -0.42
     PhpStorm
    -0.42
    POSITIVE LOGITS
     trial
    1.72
     TRIAL
    1.55
     free
    1.55
     Trial
    1.54
    Trial
    1.49
    trial
    1.48
     Free
    1.40
    Free
    1.33
     demo
    1.32
    free
    1.30
    Activations Density 0.106%

    No Known Activations