© 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. 2990
    Prev
    Next
    INDEX
    Explanations

    function and variable declarations in programming code

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

    Boolean values or flags in code snippets

    np_acts-logits-general · gemini-2.0-flash

    booleantrue/false values

    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
    存于互联网档案馆
    -0.83
    migrationBuilder
    -0.82
     itſelf
    -0.80
    +#+
    -0.78
     InputDecoration
    -0.78
    ]--;
    -0.76
     виправивши
    -0.75
     ſind
    -0.73
    RegistryLite
    -0.72
    LabelTagHelper
    -0.72
    POSITIVE LOGITS
     flag
    0.55
    Boolean
    0.51
     boolean
    0.49
    flag
    0.49
    Flag
    0.48
     témoins
    0.48
    ,
    0.47
     içinde
    0.47
     bool
    0.47
     Boolean
    0.46
    Activations Density 0.180%

    No Known Activations