© 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. 20-GEMMASCOPE-RES-16K
    11. 6826
    Prev
    Next
    INDEX
    Explanations

    phrases related to behavior and adaptation in various contexts

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

    phrases related to social adaptation and gradual normalization of behavior.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.54
     viewDidLoad
    -0.46
    ileo
    -0.45
     Italijanski
    -0.44
     intoxic
    -0.44
    MLLoader
    -0.44
    poche
    -0.43
    ロウィン
    -0.43
    راسیون
    -0.42
     ब्रेकडाउन
    -0.42
    POSITIVE LOGITS
     costumbre
    0.58
     kebiasaan
    0.50
     habit
    0.47
     familiarity
    0.47
     accustomed
    0.45
     acostumb
    0.45
    habitude
    0.45
    习惯
    0.45
     rotina
    0.44
     habitual
    0.44
    Activations Density 0.290%

    No Known Activations