© 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. 18-GEMMASCOPE-RES-16K
    11. 430
    Prev
    Next
    INDEX
    Explanations

    elements and functions related to handling and processing HTTP requests and responses in a programming context

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

    Code assignment/math operators or sanitization functions

    np_acts-logits-general · gemini-2.0-flash

    sanitizing or filtering data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     déploy
    -0.56
     produrre
    -0.53
    ecuzione
    -0.51
     Berto
    -0.50
    NoSuch
    -0.50
     Überblick
    -0.49
     Sarmiento
    -0.49
     attiva
    -0.49
    usehen
    -0.49
     rispar
    -0.48
    POSITIVE LOGITS
     filter
    0.97
     sanitized
    0.96
     cleaned
    0.93
     clean
    0.93
     saniti
    0.91
     Filter
    0.91
     sanitize
    0.88
     filtered
    0.85
     filtering
    0.83
    filter
    0.83
    Activations Density 0.386%

    No Known Activations