© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6567
    Prev
    Next
    INDEX
    Explanations

    technical terms and methodologies in research contexts, particularly those related to statistical analysis and data extraction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonUne
    -0.47
     sebagai
    -0.44
    ⓧ
    -0.37
     kaip
    -0.36
    BagConstraints
    -0.35
     ब्रेकडाउन
    -0.35
    AnimationsModule
    -0.34
    JsonPropertyName
    -0.32
    ArgsConstructor
    -0.30
     समीक्षाएं
    -0.30
    POSITIVE LOGITS
     As
    1.95
     AS
    1.90
    As
    1.82
    AS
    1.81
     Ashton
    1.71
     Ass
    1.70
     ASC
    1.64
     asy
    1.62
     ASS
    1.62
     ass
    1.59
    Activations Density 3.567%

    No Known Activations