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

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 1537
    Prev
    Next
    INDEX
    Explanations

    affirmative statements about individuals or their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     centaines
    -0.41
     dagegen
    -0.40
     néglig
    -0.38
    另一個
    -0.37
     encima
    -0.37
    ญิง
    -0.36
    jenigen
    -0.36
     Another
    -0.34
    出版年
    -0.34
     jueces
    -0.34
    POSITIVE LOGITS
     preceded
    0.73
     accompanied
    0.63
     currently
    0.60
     predeceased
    0.60
     flanked
    0.59
     known
    0.58
     fluent
    0.57
     passionate
    0.57
     kaynağından
    0.54
     headquartered
    0.54
    Activations Density 0.178%

    No Known Activations