© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8872
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to environmental conditions and their effects

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

    Environmental or weather-related conditions

    np_acts-logits-general · gemini-2.0-flash

    environmental conditions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     internally
    -0.62
     createSprite
    -0.60
    Referanser
    -0.58
    SPATH
    -0.58
    AnchorStyles
    -0.58
    richTextPanel
    -0.55
     betweenstory
    -0.55
    <unused0>
    -0.55
    delwed
    -0.54
    tyimages
    -0.54
    POSITIVE LOGITS
     conditions
    0.50
     Conditions
    0.41
     warunki
    0.41
     condições
    0.40
     markets
    0.40
     condiciones
    0.40
     Environment
    0.39
     météo
    0.38
     weather
    0.37
     environments
    0.36
    Activations Density 0.495%

    No Known Activations