© 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. 22-GEMMASCOPE-RES-16K
    6. 15476
    Prev
    Next
    INDEX
    Explanations

    mentions of "code" in various contexts

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

    "Code" and related terms ("codes", "Codemonkey")

    np_acts-logits-general · gemini-2.0-flash

    code and what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.76
    🏾
    -0.64
    يميديا
    -0.59
    ticello
    -0.58
    clearfix
    -0.56
    🏿
    -0.56
    🏽
    -0.56
    inguish
    -0.53
    ftal
    -0.53
     JAXBElement
    -0.53
    POSITIVE LOGITS
     getCode
    1.13
     codes
    1.01
     Codes
    0.99
    codes
    0.94
     setCode
    0.91
    Codes
    0.89
    getCode
    0.82
    CODE
    0.80
     CODE
    0.79
     Cod
    0.79
    Activations Density 0.100%

    No Known Activations