© 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. 40-GEMMASCOPE-RES-16K
    11. 5591
    Prev
    Next
    INDEX
    Explanations

    references to software libraries, programming languages, and data handling techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.54
    Tikang
    -0.48
    WireFormatLite
    -0.48
    PerformLayout
    -0.48
    AnchorStyles
    -0.47
     utafitiHapana
    -0.44
    __':
    -0.44
    Diweddarwch
    -0.44
    <?
    -0.43
     мәкал
    -0.43
    POSITIVE LOGITS
    /
    3.17
     /
    2.23
    ／
    1.81
    -/
    1.73
    /\
    1.70
    /"
    1.67
    /(
    1.67
    ()/
    1.66
    /-
    1.63
    /'
    1.59
    Activations Density 5.775%

    No Known Activations