© 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. 24-GEMMASCOPE-RES-16K
    11. 2441
    Prev
    Next
    INDEX
    Explanations

    references to file paths and directory structures

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

    Code file paths or directories

    np_acts-logits-general · gemini-2.0-flash

    path and directory strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.78
    WithIOException
    -0.75
    aarrggbb
    -0.74
    ]}"
    -0.64
    tagext
    -0.62
    
    -0.61
    CloseOperation
    -0.59
    numerusform
    -0.59
    ,:);
    -0.57
     }}$}
    -0.56
    POSITIVE LOGITS
     +
    0.85
    +"_
    0.67
    concat
    0.66
    +"
    0.64
    +'/
    0.62
    EndProject
    0.61
    +"/
    0.61
    ()+"
    0.61
    +'
    0.60
    +
    0.59
    Activations Density 0.150%

    No Known Activations