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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 2809
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to uncertainty or requests for information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.98
     समीक्षक
    -0.93
     Schulte
    -0.86
     Pfalz
    -0.86
    iestety
    -0.86
     تانيه
    -0.82
     мѣ
    -0.82
     Мексичка
    -0.81
    pexpr
    -0.81
    enegal
    -0.80
    POSITIVE LOGITS
    Is
    0.83
    Does
    0.83
     Does
    0.78
     Is
    0.75
     "¿
    0.71
    Do
    0.69
     apakah
    0.69
     anyone
    0.66
     Do
    0.66
    -¿
    0.65
    Activations Density 0.162%

    No Known Activations