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. 25-GEMMASCOPE-RES-16K
    6. 3836
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements in programming code, particularly those involving variable definitions and function declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Biôgrafia
    -0.58
     ujednoznacz
    -0.57
     мәкал
    -0.53
     sizeof
    -0.53
    ConverterFactory
    -0.50
    évaluateur
    -0.48
    AutoField
    -0.47
     hefyd
    -0.46
     past
    -0.46
    GEBURTSDATUM
    -0.45
    POSITIVE LOGITS
    let
    2.29
     let
    1.61
    LET
    1.38
    Let
    1.19
     Let
    1.16
     LET
    1.06
    const
    1.05
     letting
    1.01
    lets
    1.00
    letting
    0.94
    Activations Density 0.104%

    No Known Activations