© 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. 3-GEMMASCOPE-RES-16K
    11. 8322
    Prev
    Next
    INDEX
    Explanations

    references to specific documents or articles, particularly those that include categorizations, proof, or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     telinga
    -0.44
     extranjera
    -0.39
     colectiva
    -0.38
     istrinya
    -0.35
     ibunya
    -0.33
     dolayı
    -0.33
     keluarganya
    -0.33
     turística
    -0.33
     imaginación
    -0.32
     suaminya
    -0.31
    POSITIVE LOGITS
     ſind
    1.19
    ſelf
    1.17
     ſei
    1.14
    featureID
    1.14
    <pad>
    1.13
    <unused43>
    1.12
    <unused42>
    1.11
    <unused41>
    1.11
    <unused8>
    1.10
    <unused23>
    1.10
    Activations Density 1.063%

    No Known Activations