© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 4949
    Prev
    Next
    INDEX
    Explanations

    exceptions and specific programming terms related to errors and configurations

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

    exceptions and data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.71
     الحره
    -0.69
     '\\;'
    -0.68
     gynhyrchwyd
    -0.67
    uxxxx
    -0.66
    KURZBESCHREIBUNG
    -0.66
     препратки
    -0.65
     ujednoznacz
    -0.64
     ivelany
    -0.64
     للمعارف
    -0.64
    POSITIVE LOGITS
    PointerException
    0.78
    addGroup
    0.67
    AutoScaleMode
    0.62
    mtd
    0.61
    setObjectName
    0.52
    FetchType
    0.51
    TypeName
    0.50
    CastException
    0.40
    SuccessListener
    0.37
    RectangleBorder
    0.36
    Activations Density 0.000%

    No Known Activations