© 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. 35-GEMMASCOPE-RES-16K
    11. 5820
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or presence of items, often in a literary or analytical context

    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
     esternos
    -0.45
     AssemblyCompany
    -0.44
    قال
    -0.43
    asher
    -0.42
    ptid
    -0.41
     الرياضيه
    -0.40
    tagHelperRunner
    -0.40
     ModelExpression
    -0.39
    ècie
    -0.38
    δο
    -0.37
    POSITIVE LOGITS
     essentially
    0.75
     proof
    0.69
    essentially
    0.67
     enfans
    0.64
     basically
    0.63
    representative
    0.60
    tamount
    0.60
     undoubtedly
    0.59
     truly
    0.59
     akin
    0.59
    Activations Density 0.693%

    No Known Activations