© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7170
    Prev
    Next
    INDEX
    Explanations

    elements related to advocacy and charitable organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -2.73
    และ
    -1.32
     и
    -1.22
     và
    -1.20
    性和
    -1.17
     और
    -1.12
    子和
    -1.11
    力和
    -1.10
     &
    -1.10
    and
    -1.10
    POSITIVE LOGITS
    Или
    0.36
    TargetException
    0.35
    それとも
    0.34
    toMatchSnapshot
    0.34
    りする
    0.33
     sebagainya
    0.31
    Oder
    0.31
     alike
    0.31
     thereof
    0.31
    usermodel
    0.31
    Activations Density 4.183%

    No Known Activations