© 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. 20-GEMMASCOPE-RES-16K
    6. 7831
    Prev
    Next
    INDEX
    Explanations

    specific errors and troubleshooting steps related to app development and server issues

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

    "have/has/had" followed by "tried" or its variations

    np_acts-logits-general · gemini-2.0-flash

    I have tried

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.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
    nthesis
    -0.83
    argout
    -0.65
     survi
    -0.60
    findpost
    -0.60
     onItemClick
    -0.59
     Selections
    -0.57
     wanting
    -0.56
     desiring
    -0.56
     favorably
    -0.54
    iteter
    -0.52
    POSITIVE LOGITS
     checked
    0.82
     Checked
    0.80
     tried
    0.79
     Tried
    0.73
     check
    0.73
    Checked
    0.72
     Try
    0.71
    tried
    0.69
    Tried
    0.68
     Check
    0.68
    Activations Density 0.242%

    No Known Activations