© 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. 2832
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance metrics and evaluations

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

    Followed by conjunctions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    and conjunctions

    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
     maupun
    -0.60
     lẫn
    -0.54
    sowie
    -0.46
    copg
    -0.45
    vignon
    -0.44
     siehe
    -0.43
    NamedQueries
    -0.40
    ']='
    -0.39
     voire
    -0.39
     bzw
    -0.39
    POSITIVE LOGITS
     and
    1.02
     And
    1.00
    And
    0.87
     והוא
    0.86
    性和
    0.85
     และ
    0.84
    이고
    0.79
    并且
    0.78
    子和
    0.74
    力和
    0.73
    Activations Density 5.198%

    No Known Activations