Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 559
    Prev
    Next
    INDEX
    Explanations

    phrases relating to legal proceedings and arguments

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

    disagreement or opposition

    np_acts-logits-general · gemini-2.0-flash

    opponents of affirmative action, lawsuits

    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
    :✨
    -0.56
     pleaſure
    -0.54
     Normdatei
    -0.54
    Personendaten
    -0.54
     tartalomajánló
    -0.53
     purpoſe
    -0.50
     ſtand
    -0.49
     Wicidata
    -0.49
    OrNil
    -0.48
    styleType
    -0.48
    POSITIVE LOGITS
     confronted
    0.44
     dissatisfied
    0.40
     angry
    0.40
     discontent
    0.39
     dissatisfaction
    0.39
    spaceBetween
    0.37
     confront
    0.37
     agrav
    0.36
     referendum
    0.36
     protestors
    0.36
    Activations Density 0.640%

    No Known Activations