© 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. 24-GEMMASCOPE-RES-16K
    11. 9384
    Prev
    Next
    INDEX
    Explanations

    academic language related to research methodologies and theoretical frameworks

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

    followed by "is," "to," or "in"

    np_acts-logits-general · gemini-2.0-flash

    explaining issues and concepts

    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
    MigrationBuilder
    -0.69
     houſe
    -0.60
     amper
    -0.58
    multirow
    -0.56
    ſchen
    -0.56
    PDB
    -0.55
     emojis
    -0.54
    septic
    -0.54
     LGBTQ
    -0.54
     XNUMX
    -0.53
    POSITIVE LOGITS
     zwią
    0.42
     изпол
    0.38
     AssemblyTitle
    0.37
     öner
    0.37
     conceptually
    0.36
     Einstellung
    0.36
    masalahan
    0.36
     Vorles
    0.36
     generality
    0.36
    sepeda
    0.35
    Activations Density 2.966%

    No Known Activations