© 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. 15-GEMMASCOPE-RES-16K
    6. 1336
    Prev
    Next
    INDEX
    Explanations

    programming-related code patterns and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enseur
    -0.44
     vym
    -0.43
    apunov
    -0.42
    fertigung
    -0.41
    ktm
    -0.41
     due
    -0.40
     vainilla
    -0.40
    trans
    -0.40
     scha
    -0.39
     fous
    -0.39
    POSITIVE LOGITS
     argv
    0.95
    argv
    0.90
     command
    0.88
    yargs
    0.85
     Commands
    0.84
     commands
    0.81
     Command
    0.80
    ARGV
    0.79
     cmd
    0.77
     COMMAND
    0.77
    Activations Density 0.222%

    No Known Activations