© 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. 11139
    Prev
    Next
    INDEX
    Explanations

    second-person pronouns and related phrases about personal advice or actions

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

    Tokens appearing before auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    you can, you could, you want

    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
     étoit
    -0.47
     bluzka
    -0.46
     gynnwys
    -0.46
     ſtre
    -0.45
    ſelves
    -0.45
     myſelf
    -0.45
     themſelves
    -0.43
     ſte
    -0.42
    felves
    -0.42
    MigrationBuilder
    -0.41
    POSITIVE LOGITS
     rarely
    0.57
     seldom
    0.54
     Rarely
    0.48
     can
    0.47
     hear
    0.45
     cannot
    0.45
     gotta
    0.44
     hardly
    0.44
    ########.
    0.44
     mustn
    0.44
    Activations Density 0.210%

    No Known Activations