© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 7999
    Prev
    Next
    INDEX
    Explanations

    concepts related to quantities and community impact

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

    Preceding certain verbs

    np_acts-logits-general · gemini-2.0-flash

    goals and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.45
    faßt
    -0.40
    IVEREF
    -0.40
    SuspendLayout
    -0.39
    pushFollow
    -0.39
    umably
    -0.37
     ब्रेकडाउन
    -0.36
    onViewCreated
    -0.36
     informée
    -0.36
     geb
    -0.35
    POSITIVE LOGITS
     everything
    0.61
    everything
    0.54
    Everything
    0.50
     totul
    0.49
     Everything
    0.49
     EVERYTHING
    0.49
     Мексичка
    0.47
    ivore
    0.46
    RTCF
    0.45
     realities
    0.44
    Activations Density 0.442%

    No Known Activations