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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6410
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "pre" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.54
    tschaft
    -0.49
    ValueStyle
    -0.48
    yntaxException
    -0.46
    ckså
    -0.44
    áctenos
    -0.44
    atorship
    -0.44
     للمعارف
    -0.44
    SourceChecksum
    -0.43
    zación
    -0.43
    POSITIVE LOGITS
     Pre
    3.25
     pre
    3.17
    Pre
    3.11
    pre
    3.08
     PRE
    2.66
    PRE
    2.52
     pré
    2.05
    预
    1.89
     Pré
    1.63
     预
    1.63
    Activations Density 0.070%

    No Known Activations