© 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. 15191
    Prev
    Next
    INDEX
    Explanations

    elements related to technology and integration

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

    followed by prepositions "into," "onto," or "beyond."

    np_acts-logits-general · gemini-2.0-flash

    into, onto, to

    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
    rungsseite
    -0.68
    EndInit
    -0.52
     ModelExpression
    -0.51
    хьтан
    -0.50
    ViewImports
    -0.49
     ujednoznacz
    -0.48
     SDLK
    -0.47
     INTERESAR
    -0.46
    AndEndTag
    -0.46
    juvant
    -0.46
    POSITIVE LOGITS
     into
    1.34
     onto
    1.28
    into
    0.92
     vào
    0.90
     Into
    0.82
    Into
    0.81
     INTO
    0.79
     lên
    0.70
    onto
    0.66
     unto
    0.66
    Activations Density 1.200%

    No Known Activations