© 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 EvalsExportsAPI 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. 10273
    Prev
    Next
    INDEX
    Explanations

    technical terms and coding structures related to binary data and encoding

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

    Code snippets with bitfields/bitmasking

    np_acts-logits-general · gemini-2.0-flash

    choice and fit

    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
     оригіналу
    -0.44
    จ
    -0.36
    CGContext
    -0.36
    chemise
    -0.35
    AutoField
    -0.32
     blogs
    -0.31
    #+#
    -0.31
    migrationBuilder
    -0.31
    literals
    -0.31
    amazonaws
    -0.30
    POSITIVE LOGITS
    InjectAttribute
    0.59
     Италијани
    0.56
     resourceCulture
    0.52
     Chriftian
    0.51
    GTCX
    0.51
     Савезне
    0.50
     censiti
    0.48
     tornado
    0.47
    uxxxx
    0.46
    ̍
    0.46
    Activations Density 2.328%

    No Known Activations