© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5453
    Prev
    Next
    INDEX
    Explanations

    terms related to physical properties and processes involving materials and manufacturing techniques

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

    Physical indentations or perforations

    np_acts-logits-general · gemini-2.0-flash

    holes, indentations, lines

    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
    cartão
    -0.41
     Jurí
    -0.41
     خارجية
    -0.39
     való
    -0.38
     fornecer
    -0.38
     assistir
    -0.37
    ReusableCell
    -0.37
    atmosphère
    -0.36
    NgModule
    -0.36
     Tiempo
    -0.36
    POSITIVE LOGITS
     gynhyrchwyd
    0.75
     holes
    0.68
     spots
    0.67
     dots
    0.64
    holes
    0.62
     patterns
    0.59
    spots
    0.59
     ExecuteAsync
    0.59
     pattern
    0.58
    BagLayout
    0.57
    Activations Density 0.644%

    No Known Activations