© 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. 31-GEMMASCOPE-RES-16K
    11. 8014
    Prev
    Next
    INDEX
    Explanations

    affirmations and rhetorical questions that seek agreement or validation

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

    rhetorical questions or confirmatory statements seeking agreement, typically ending with "right?" or "yes?".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.54
    httphttps
    -0.50
    VYMaps
    -0.48
    AccessorTable
    -0.47
    )}}{
    -0.47
    RegressionTest
    -0.46
    ſelves
    -0.46
    Сылтамалар
    -0.46
    FieldNumber
    -0.46
    تقاوى
    -0.45
    POSITIVE LOGITS
    ?,
    0.69
    ?.
    0.60
    ؟
    0.57
    ?;
    0.51
    ?).
    0.49
    ?)
    0.45
    ?!
    0.45
    ؟؟
    0.45
    ?:
    0.44
    ?-
    0.44
    Activations Density 0.140%

    No Known Activations