© 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. 4548
    Prev
    Next
    INDEX
    Explanations

    key concepts and themes related to priorities, financial issues, and future planning

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

    words related to future plans or actions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    ConstraintMaker
    -0.57
     CreateTagHelper
    -0.55
     AssemblyTitle
    -0.54
     '\\;'
    -0.54
    AndEndTag
    -0.46
    Попис
    -0.45
    nloa
    -0.45
     обо
    -0.44
    UrlResolution
    -0.43
    ModelAdmin
    -0.43
    POSITIVE LOGITS
     topic
    0.66
     Topic
    0.55
    Topic
    0.50
    /**
    0.47
     subject
    0.45
    topic
    0.43
    velt
    0.43
     TOPIC
    0.40
     Weller
    0.40
    待
    0.39
    Activations Density 0.457%

    No Known Activations