© 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. 28-GEMMASCOPE-RES-16K
    11. 3888
    Prev
    Next
    INDEX
    Explanations

    instances of the word "where" indicating locations or contexts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows the word "where"

    np_acts-logits-general · gemini-2.0-flash

    where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SdkVersion
    -0.45
    НС
    -0.42
    Audit
    -0.40
     LTS
    -0.40
    tisgarh
    -0.40
    Philipp
    -0.39
     SMS
    -0.39
     Gymnastics
    -0.39
     Athletic
    -0.39
    ランク
    -0.39
    POSITIVE LOGITS
    where
    0.93
    WHERE
    0.87
    Where
    0.80
     where
    0.75
    Dónde
    0.73
    Où
    0.72
     Where
    0.71
     WHERE
    0.68
     Où
    0.63
    dónde
    0.62
    Activations Density 0.122%

    No Known Activations