© 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. 2858
    Prev
    Next
    INDEX
    Explanations

    comparative phrases highlighting expected outcomes or results

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

    following "as," often "expected" or a synonym

    np_acts-logits-general · gemini-2.0-flash

    as expected

    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
     uſed
    -0.65
    UserScript
    -0.60
     autorytatywna
    -0.56
     myſelf
    -0.53
    ########.
    -0.52
     raiſ
    -0.50
     informée
    -0.50
    __*/
    -0.48
     &___
    -0.48
     deſt
    -0.48
    POSITIVE LOGITS
     expected
    1.45
    expected
    1.30
     unsur
    1.29
     predictable
    1.21
    Expected
    1.13
    意料
    1.12
     Expected
    1.12
     EXPECT
    0.91
     esperado
    0.90
     expect
    0.90
    Activations Density 0.455%

    No Known Activations