© 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. 14313
    Prev
    Next
    INDEX
    Explanations

    syntactical structures commonly used in programming code

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

    Non-English words and code elements

    np_acts-logits-general · gemini-2.0-flash

    Oushi, imported, migrationBuilder

    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
    RegressionTest
    -0.81
    )。
    -0.64
    UnsafeEnabled
    -0.64
    ）。
    -0.61
    </s>
    -0.59
    ).]
    -0.59
    
    -0.58
    )];
    -0.57
    )]$
    -0.57
    Історія
    -0.57
    POSITIVE LOGITS
    وردار
    0.65
    IMPORTED
    0.62
    migrationBuilder
    0.51
    ستون
    0.50
    ULUS
    0.50
    LayoutStyle
    0.47
    ネート
    0.46
    InstanceState
    0.45
     Joining
    0.45
    Joining
    0.45
    Activations Density 0.028%

    No Known Activations