© 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. 25-GEMMASCOPE-RES-16K
    11. 2562
    Prev
    Next
    INDEX
    Explanations

    code-related constructs, specifically access modifiers and keywords associated with constant definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.55
    ("")]
    -0.53
    렸
    -0.52
    }^{-}\
    -0.52
     ExecuteAsync
    -0.52
    inheritDoc
    -0.52
    MockMvc
    -0.51
    ientí
    -0.51
    UserScript
    -0.49
    Ordinary
    -0.49
    POSITIVE LOGITS
     static
    2.18
    static
    2.13
    静态
    1.31
    Static
    1.23
     Static
    1.16
     STATIC
    1.10
    STATIC
    1.05
    staticmethod
    1.03
     静
    1.02
     stationary
    0.88
    Activations Density 0.115%

    No Known Activations