© 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. 14286
    Prev
    Next
    INDEX
    Explanations

    code references and method calls in programming contexts

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

    Code, system commands, or programming

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and structure

    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
    <bos>
    -0.72
    IMPORTED
    -0.58
    oredCriteria
    -0.57
    RetentionPolicy
    -0.48
    AndroidJUnit
    -0.48
    Хьажоргаш
    -0.47
     ujednoznacz
    -0.44
    mobileqq
    -0.43
    Collegamenti
    -0.42
    endforeach
    -0.42
    POSITIVE LOGITS
    AccessorTable
    0.80
    setVerticalGroup
    0.60
    LOGGER
    0.60
    ScopeManager
    0.59
    AddHtmlAttribute
    0.59
    󠁿
    0.58
    ])));
    0.58
    Hozzáférés
    0.57
    saraba
    0.56
     CreateTagHelper
    0.55
    Activations Density 0.096%

    No Known Activations