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

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 10087
    Prev
    Next
    INDEX
    Explanations

    words that suggest extreme or negative emotions or actions

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

    following single letters

    np_acts-logits-general · gemini-2.0-flash

    yuck, fucking, gotta, freakin, ooo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -1.09
    AndEndTag
    -1.07
    <unused3>
    -1.02
     imagui
    -1.02
    <unused28>
    -1.02
    <pad>
    -1.02
    <unused42>
    -1.02
    <unused43>
    -1.02
    <unused41>
    -1.02
    [@BOS@]
    -1.01
    POSITIVE LOGITS
    oooo
    0.41
     freakin
    0.40
     gonna
    0.38
     freaking
    0.38
    oooooo
    0.34
     fucking
    0.34
    oooooooo
    0.34
     cuz
    0.33
    en
    0.32
     gotta
    0.32
    Activations Density 0.551%

    No Known Activations