© 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. 8-GEMMASCOPE-RES-16K
    6. 6526
    Prev
    Next
    INDEX
    Explanations

    statements presenting facts or observations about situations that are characterized as notable or problematic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.81
    GEBURTS
    -0.75
     <<<<<<<<<<<<<<
    -0.68
     Normdatei
    -0.64
     Мексичка
    -0.60
     propOrder
    -0.59
     ویکی‌پدی
    -0.58
    SourceChecksum
    -0.54
    djangoproject
    -0.54
     يتيمه
    -0.53
    POSITIVE LOGITS
     helyzet
    0.46
     problemet
    0.36
    PathVariable
    0.35
    偏偏
    0.35
     problem
    0.35
     sharpness
    0.34
    Anyhow
    0.34
    autant
    0.34
     toughest
    0.34
     PO
    0.33
    Activations Density 0.335%

    No Known Activations