© 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. 28-GEMMASCOPE-RES-16K
    11. 10350
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to biological research and methodologies

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

    followed by suffixes like -s, -ed, -ing, -er, -ly

    np_acts-logits-general · gemini-2.0-flash

    nouns describing entities or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.42
    W
    -0.40
     totalSupply
    -0.38
    StructEnd
    -0.38
    ┛
    -0.38
    IS
    -0.37
     Renegade
    -0.37
    醐
    -0.36
    OpenHelper
    -0.36
    CIS
    -0.36
    POSITIVE LOGITS
     betweenstory
    0.79
    transQ
    0.74
    fromnode
    0.69
     desmotivaciones
    0.65
    請繼續往下閱讀
    0.61
    colgante
    0.59
     nonUne
    0.58
    pulseira
    0.58
     saveiro
    0.57
    pecabe
    0.57
    Activations Density 8.000%

    No Known Activations