© 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. 3-GEMMASCOPE-RES-16K
    11. 5801
    Prev
    Next
    INDEX
    Explanations

    concepts and terminology related to credit and financing services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.52
    lapsingToolbar
    -0.52
     EconPapers
    -0.50
    fjspx
    -0.49
     ModelExpression
    -0.49
     ब्रेकडाउन
    -0.48
    drawiam
    -0.47
     onPostExecute
    -0.45
    HasIndex
    -0.45
    SharedModule
    -0.45
    POSITIVE LOGITS
    mergeFrom
    0.42
    IUrlHelper
    0.41
    GEBURTSDATUM
    0.38
    SharedDtor
    0.38
    tvguidetime
    0.37
    Likewise
    0.37
    Референце
    0.37
     likewise
    0.34
    '%(
    0.34
    getMenuInflater
    0.34
    Activations Density 0.503%

    No Known Activations