© 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. 38-GEMMASCOPE-RES-16K
    6. 7311
    Prev
    Next
    INDEX
    Explanations

    references to specific species and their scientific classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onCreateView
    -0.60
    ChildScrollView
    -0.53
    :✨
    -0.49
     tartalomajánló
    -0.48
    Eagle
    -0.47
    eagle
    -0.47
     Eagle
    -0.47
     становника
    -0.46
    principalTable
    -0.46
    UnsafeEnabled
    -0.45
    POSITIVE LOGITS
    eterangan
    0.41
     throat
    0.39
    喉
    0.39
     patch
    0.39
     Patch
    0.38
    patch
    0.37
    Patch
    0.37
    ruf
    0.36
     patching
    0.35
     Streak
    0.35
    Activations Density 0.303%

    No Known Activations