© 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 EvalsExportsinterp-engineNEWAPI 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. 15189
    Prev
    Next
    INDEX
    Explanations

    negative qualifiers and phrases that express a lack of certainty or positivity

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

    preceding "be" or forms of "be"

    np_acts-logits-general · gemini-2.0-flash

    not be

    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
    aimana
    -0.59
    chieht
    -0.53
     виправивши
    -0.53
    ագրություններ
    -0.53
     zijne
    -0.52
     zoude
    -0.52
     pecados
    -0.47
     casó
    -0.47
     dezelve
    -0.47
     bientôt
    -0.47
    POSITIVE LOGITS
     be
    0.83
     become
    0.56
     been
    0.54
     reflect
    0.53
     come
    0.51
     mobilize
    0.50
     interfere
    0.50
     justify
    0.49
     succeed
    0.49
     have
    0.49
    Activations Density 0.302%

    No Known Activations