© 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. 8167
    Prev
    Next
    INDEX
    Explanations

    phrases related to precise mechanisms and engineering details

    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
    Slf
    -0.40
    strix
    -0.37
    composición
    -0.33
     PyTuple
    -0.32
     Wiktionnaire
    -0.30
     ramo
    -0.30
     survie
    -0.29
    winston
    -0.28
     tarz
    -0.28
     Synthe
    -0.28
    POSITIVE LOGITS
     alignment
    1.94
     Alignment
    1.73
     aligning
    1.64
     align
    1.61
     alignments
    1.61
     aligned
    1.60
     ALIGN
    1.59
    Alignment
    1.55
     Align
    1.54
    alignment
    1.53
    Activations Density 0.649%

    No Known Activations