© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15903
    Prev
    Next
    INDEX
    Explanations

    requests for assistance and expressions of gratitude

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

    polite expressions of gratitude and requests for help in online forums and discussions.

    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
    uronic
    -0.37
    +#+
    -0.37
    ::_('
    -0.36
    runOnUiThread
    -0.34
    bootstrapcdn
    -0.33
    uom
    -0.33
     Distillery
    -0.32
     dags
    -0.32
    Broad
    -0.32
    zy
    -0.31
    POSITIVE LOGITS
     thank
    3.31
     Thank
    2.91
     thanks
    2.75
    Thank
    2.69
    thank
    2.66
     thanked
    2.55
     THANK
    2.52
     Thanks
    2.48
     thanking
    2.42
    thanks
    2.41
    Activations Density 0.470%

    No Known Activations