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. 0-GEMMASCOPE-RES-16K
    6. 2920
    Prev
    Next
    INDEX
    Explanations

    key features or important elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fellow
    -0.38
    ;->
    -0.36
     fixture
    -0.35
     φυ
    -0.34
    Посилання
    -0.33
     Peers
    -0.33
    SuspendLayout
    -0.32
     peers
    -0.32
     ]];
    -0.32
    ₱
    -0.31
    POSITIVE LOGITS
     aspect
    0.88
    aspect
    0.78
     Aspect
    0.68
    Aspect
    0.67
     involved
    0.66
     involvement
    0.65
    involved
    0.65
     INVOLVED
    0.64
     Allocate
    0.64
     allocated
    0.64
    Activations Density 0.288%

    No Known Activations