© 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. 24-GEMMASCOPE-RES-16K
    6. 12461
    Prev
    Next
    INDEX
    Explanations

    technical function signatures and parameters related to code

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

    `@param` or `@prop` followed by `{Object}`

    np_acts-logits-general · gemini-2.0-flash

    url, options, or return descriptions

    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
    enumi
    -0.93
    LookAnd
    -0.72
     AssemblyProduct
    -0.71
    StoryboardSegue
    -0.66
    enumii
    -0.62
    AccessorTable
    -0.61
    
    -0.59
    setVerticalGroup
    -0.58
    IUrlHelper
    -0.58
    lapsingToolbar
    -0.56
    POSITIVE LOGITS
     Specifies
    0.89
     Indicates
    0.84
     specifies
    0.83
     Optional
    0.80
    Specifies
    0.79
     indicates
    0.78
     Describes
    0.78
     optional
    0.77
    optional
    0.77
    indicates
    0.76
    Activations Density 0.412%

    No Known Activations