© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 14019
    Prev
    Next
    INDEX
    Explanations

    references to forms, fields, and actions related to filling out or processing data inputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewLabel
    -0.46
    LookAnd
    -0.44
     invokingState
    -0.42
    IndentedString
    -0.42
     muualla
    -0.41
    DECREF
    -0.40
     فريبيس
    -0.37
    Cyfarwyddwr
    -0.36
     ExecuteAsync
    -0.36
     strconv
    -0.36
    POSITIVE LOGITS
     filling
    3.66
     fill
    3.55
     fills
    3.31
     Fill
    3.30
     Filling
    3.30
    Filling
    3.16
     filled
    3.14
    Fill
    3.13
    fill
    3.06
     FILL
    3.03
    Activations Density 1.079%

    No Known Activations