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. 1522
    Prev
    Next
    INDEX
    Explanations

    expressions of complex emotional and social dynamics in discussions

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

    arguments or viewpoints

    np_acts-logits-general · gemini-2.0-flash

    different perspectives and arguments

    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
    WithIOException
    -0.50
    rrggbb
    -0.48
     dép
    -0.44
     للاسماء
    -0.44
    verifyException
    -0.41
    SneakyThrows
    -0.39
     penyel
    -0.39
     кӀ
    -0.39
    nungszeiten
    -0.39
     defStyle
    -0.38
    POSITIVE LOGITS
    期刊论文
    0.65
    HomeAsUpEnabled
    0.60
     arguments
    0.54
     objectivity
    0.49
     argumentos
    0.49
     reasoned
    0.48
     argument
    0.47
     prejudiced
    0.46
     biased
    0.45
     debate
    0.45
    Activations Density 0.923%

    No Known Activations