© 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. 35-GEMMASCOPE-RES-16K
    6. 14713
    Prev
    Next
    INDEX
    Explanations

    terms related to prediction and model output in machine learning contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.60
     صوتيه
    -0.48
     surla
    -0.47
    Datuak
    -0.45
     noten
    -0.44
     estekak
    -0.44
    ########.
    -0.43
     Administrativna
    -0.43
    Przypisy
    -0.42
    ElementException
    -0.42
    POSITIVE LOGITS
     labels
    0.94
     binary
    0.81
     classification
    0.79
     classifications
    0.74
     Labels
    0.74
     softmax
    0.74
     label
    0.73
    labels
    0.70
     Binary
    0.69
    Labels
    0.68
    Activations Density 0.259%

    No Known Activations