© 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. 14157
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax and structure

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

    "case" or "default" statement in code or logic

    np_acts-logits-general · gemini-2.0-flash

    this case

    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
    sidemargin
    -0.76
    DispatchToProps
    -0.74
    InjectAttribute
    -0.74
    UnusedPrivate
    -0.74
    writeFieldEnd
    -0.73
    OGND
    -0.73
    mybatisplus
    -0.71
    LookAnd
    -0.71
    HasAnnotation
    -0.71
    }],
    -0.71
    POSITIVE LOGITS
     case
    3.32
    case
    2.94
    Case
    2.63
     Case
    2.59
     cases
    2.58
     caso
    2.50
     CASE
    2.28
    CASE
    2.26
     Cases
    2.19
    cases
    2.13
    Activations Density 0.714%

    No Known Activations