© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8657
    Prev
    Next
    INDEX
    Explanations

    key components and relationships in complex systems or processes

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

    noun phrases involving the words "part of" or similar constructions describing components of a larger system.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.48
    
    -0.41
     nonUne
    -0.41
    OpenHelper
    -0.37
    KommentareTeilen
    -0.37
    pendenti
    -0.36
    kannya
    -0.36
    users
    -0.36
    +#+#
    -0.36
     сбо
    -0.36
    POSITIVE LOGITS
    writeFieldEnd
    0.49
     onAnimation
    0.48
     мәкал
    0.47
    homonymie
    0.44
    waitKey
    0.44
    IBarButtonItem
    0.42
     modelAndView
    0.42
    ękuję
    0.41
     culturales
    0.40
    bosity
    0.40
    Activations Density 0.608%

    No Known Activations