© 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. 8084
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate chances or probabilities of outcomes

    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
     AssemblyCompany
    -0.55
    complexContent
    -0.48
    tagHelperRunner
    -0.46
     Wikiseite
    -0.45
    ItemBackground
    -0.45
    jména
    -0.44
    ########.
    -0.43
    يكب
    -0.43
     Мексичка
    -0.40
     sumpay
    -0.40
    POSITIVE LOGITS
     chances
    3.14
     chance
    2.94
     Chances
    2.56
     probability
    2.53
    chance
    2.47
    Chances
    2.38
     Chance
    2.31
     likelihood
    2.31
    Chance
    2.25
     odds
    2.22
    Activations Density 0.580%

    No Known Activations