© 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. 24-GEMMASCOPE-RES-16K
    11. 13845
    Prev
    Next
    INDEX
    Explanations

    specific assembly attributes and properties in code-related texts

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

    Code-related assembly and programming terms

    np_acts-logits-general · gemini-2.0-flash

    code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.82
     Мексичка
    -0.71
    waitKey
    -0.69
    EDEFAULT
    -0.65
    NewUrlParser
    -0.65
    brigens
    -0.60
     виправивши
    -0.60
     sessionFactory
    -0.59
    basicConfig
    -0.59
    WriteBarrier
    -0.59
    POSITIVE LOGITS
    ↵
    0.60
    uminense
    0.57
     useRouter
    0.47
     invokingState
    0.46
     ABI
    0.45
    REASONS
    0.44
     Uniform
    0.43
     Synod
    0.43
     Turi
    0.43
     SCN
    0.42
    Activations Density 0.021%

    No Known Activations