© 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. 12-GEMMASCOPE-RES-16K
    6. 5740
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to digital and analog conversion processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antMatchers
    -0.39
     تانيه
    -0.39
    AddWithValue
    -0.37
    :✨
    -0.37
     חיצוניים
    -0.36
     infil
    -0.34
     consultato
    -0.34
     Erziehung
    -0.33
    原始内容存档于
    -0.32
    出版年
    -0.32
    POSITIVE LOGITS
    TagMode
    0.59
    endcsname
    0.56
    djangoproject
    0.55
     okuyayım
    0.54
    rungsseite
    0.53
    QPalette
    0.52
     Lovato
    0.49
    ☸
    0.47
     Autorisations
    0.47
    polation
    0.47
    Activations Density 1.103%

    No Known Activations