© 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. 1565
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of introspection about motivations and justifications

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

    Why something started in the first place

    np_acts-logits-general · gemini-2.0-flash

    in the first place

    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
    WebElementEntity
    -0.48
    cydow
    -0.45
    henswürdigkeiten
    -0.41
    出版年
    -0.37
    sidemargin
    -0.36
    KEYCODE
    -0.36
     gré
    -0.35
    Erstellt
    -0.35
    sivité
    -0.35
    MENAFN
    -0.35
    POSITIVE LOGITS
    そもそも
    1.15
     anyway
    1.07
     anyways
    1.03
     originally
    0.90
     überhaupt
    0.90
    anyway
    0.87
     anyhow
    0.87
     Anyway
    0.83
     Anyways
    0.82
     вообще
    0.81
    Activations Density 0.361%

    No Known Activations