Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4060
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and code snippets

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

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    code snippets and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.68
     unknownFields
    -0.58
    verifyException
    -0.57
    IndentedString
    -0.56
    ArgsConstructor
    -0.55
     SafeMath
    -0.55
    FunctionFlags
    -0.55
    verwijspagina
    -0.54
    CppCodeGen
    -0.53
    windowFixed
    -0.52
    POSITIVE LOGITS
    Fac
    0.37
    署
    0.36
     Agg
    0.36
    徊
    0.35
     Stö
    0.35
     Ped
    0.34
    Succeeded
    0.34
     démo
    0.33
    Agg
    0.33
     FAC
    0.33
    Activations Density 0.710%

    No Known Activations