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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11867
    Prev
    Next
    INDEX
    Explanations

    instances of specific mathematical concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pu
    -0.39
    ẳn
    -0.39
     &___
    -0.38
    mø
    -0.38
    laient
    -0.38
    MarshalTo
    -0.37
     THREAD
    -0.37
    lesias
    -0.36
    Problemas
    -0.36
    MemoryWarning
    -0.35
    POSITIVE LOGITS
     MainAxisSize
    0.60
    +#+
    0.52
    ########.
    0.49
    DebuggerNonUser
    0.47
     endblock
    0.46
     ostavi
    0.45
     चीज़ों
    0.44
    endpush
    0.44
    章节错误
    0.44
    匿名使用者
    0.43
    Activations Density 0.447%

    No Known Activations