© 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. 36-GEMMASCOPE-RES-16K
    6. 7888
    Prev
    Next
    INDEX
    Explanations

    statements indicating the existence or presence of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paesi
    -0.44
     Paused
    -0.43
     SafeMath
    -0.42
    routeProvider
    -0.41
    mbols
    -0.41
     setEmail
    -0.41
    affaires
    -0.41
    GeneratedMessage
    -0.40
    HasIndex
    -0.40
     déclaration
    -0.39
    POSITIVE LOGITS
     are
    1.30
    are
    0.58
     são
    0.57
     vannak
    0.55
     sono
    0.55
     Are
    0.54
     jsou
    0.53
    Are
    0.53
     هستند
    0.52
     są
    0.52
    Activations Density 0.156%

    No Known Activations