© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12148
    Prev
    Next
    INDEX
    Explanations

    elements associated with cautionary language or statements

    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
    :✨
    -0.69
    SequentialGroup
    -0.63
    EndContext
    -0.45
     Administrativna
    -0.37
    apnews
    -0.36
    PreferredItem
    -0.35
    mockMvc
    -0.34
    closePath
    -0.33
    zerne
    -0.32
    SharedCtor
    -0.32
    POSITIVE LOGITS
     speak
    3.13
     speaking
    3.09
     speaks
    2.64
    speaking
    2.61
     Speak
    2.59
     Speaking
    2.58
     spoke
    2.55
    speak
    2.52
     talk
    2.50
     talking
    2.48
    Activations Density 0.684%

    No Known Activations