© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5755
    Prev
    Next
    INDEX
    Explanations

    programming constructs such as definitions, types, namespaces, and string literals

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

    Strings starting with quotation marks or special characters

    np_acts-logits-general · gemini-2.0-flash

    code identifiers after quotes/punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    ic
    -0.44
    ome
    -0.39
     kept
    -0.37
     brought
    -0.37
    hler
    -0.36
    گانی
    -0.35
     admitted
    -0.35
     led
    -0.35
     ran
    -0.35
    ay
    -0.35
    POSITIVE LOGITS
    VersionUID
    0.74
     AssemblyProduct
    0.72
     BoxFit
    0.70
     AssemblyTitle
    0.65
    ConstraintMaker
    0.64
     transférez
    0.63
     kasarigan
    0.62
    Personendaten
    0.61
     MainAxisSize
    0.61
    ReusableCell
    0.59
    Activations Density 0.425%

    No Known Activations