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. 3-GEMMASCOPE-RES-16K
    6. 6058
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "points" and related terms referring to scoring or metrics

    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
    MLLoader
    -0.68
    bitat
    -0.50
     utafitiHapana
    -0.45
     kandang
    -0.40
    stunde
    -0.39
    Tembelea
    -0.38
     tracción
    -0.38
    Bibliograf
    -0.37
    视角
    -0.37
    Offic
    -0.36
    POSITIVE LOGITS
     points
    3.03
     Points
    2.67
    Points
    2.64
    points
    2.50
     POINTS
    2.39
    POINTS
    2.09
     puntos
    1.84
     Punkte
    1.83
     punten
    1.66
     pontos
    1.55
    Activations Density 0.128%

    No Known Activations