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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8612
    Prev
    Next
    INDEX
    Explanations

    references to various types of platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imread
    -0.32
    Jsp
    -0.31
    SerializeField
    -0.31
     diş
    -0.30
     NoSuch
    -0.30
    ()");
    -0.30
    achella
    -0.30
    acute
    -0.30
     asupra
    -0.30
    bcryptjs
    -0.30
    POSITIVE LOGITS
     platform
    4.16
     Platform
    3.73
    platform
    3.72
    Platform
    3.55
     platforms
    3.53
     PLATFORM
    3.47
     Platforms
    3.30
     plataforma
    3.19
     Plattform
    3.14
    平台
    3.03
    Activations Density 0.045%

    No Known Activations