Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2343
    Prev
    Next
    INDEX
    Explanations

    syntax elements and operators in code

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

    Code-related tokens and terms

    np_acts-logits-general · gemini-2.0-flash

    programming utilities and libraries

    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
     nakalista
    -0.94
     disambiguazione
    -0.93
     dAtA
    -0.86
    awtextra
    -0.82
    parsedMessage
    -0.82
     Roskov
    -0.78
     resourceCulture
    -0.77
     ModelExpression
    -0.75
    ContentAsync
    -0.74
    WriteAttribute
    -0.71
    POSITIVE LOGITS
    java
    0.61
     java
    0.59
    Utils
    0.57
    Helper
    0.53
    apache
    0.49
    Util
    0.49
    Funcs
    0.47
    util
    0.47
    Helpers
    0.46
    utils
    0.45
    Activations Density 0.126%

    No Known Activations