© 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. 8137
    Prev
    Next
    INDEX
    Explanations

    references to the term "Ver" and variations of it, indicating a focus on verification or validation concepts

    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
    haltens
    -0.58
     FetchType
    -0.57
    mögens
    -0.55
    bleib
    -0.49
    WebElementEntity
    -0.47
    stdc
    -0.46
    pozdrawiam
    -0.45
    StackNavigator
    -0.45
    BASEPATH
    -0.45
    TagMode
    -0.45
    POSITIVE LOGITS
     Ver
    0.68
    Ver
    0.65
     VER
    0.59
     ver
    0.56
     Vern
    0.50
    Vern
    0.48
     Verr
    0.45
     Verm
    0.43
    VER
    0.43
     Verma
    0.43
    Activations Density 0.197%

    No Known Activations