© 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. 28-GEMMASCOPE-RES-16K
    6. 4001
    Prev
    Next
    INDEX
    Explanations

    concepts related to belief and understanding within diverse perspectives

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

    Follows punctuation

    np_acts-logits-general · gemini-2.0-flash

    human or everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    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
    -0.73
    haikusbot
    -0.72
     defaultstate
    -0.67
     utafitiHapana
    -0.61
    aarrggbb
    -0.61
     surla
    -0.60
    parsedMessage
    -0.60
    postsleuth
    -0.59
     للمعارف
    -0.59
     otomatig
    -0.57
    POSITIVE LOGITS
     manusia
    0.60
     life
    0.52
     human
    0.50
     ultimately
    0.49
     humans
    0.49
     sometimes
    0.49
     männis
    0.49
     every
    0.48
    每个人
    0.44
    Every
    0.44
    Activations Density 0.668%

    No Known Activations