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-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 13604
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to programming and APIs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PropertyChanging
    -0.64
     Exactos
    -0.61
     bahía
    -0.57
     FishBase
    -0.57
    ("$.
    -0.56
    ftagPool
    -0.56
     centrale
    -0.55
    цима
    -0.55
    caten
    -0.55
     stratégique
    -0.54
    POSITIVE LOGITS
    Tikang
    0.76
    Skocz
    0.72
    Hochspringen
    0.65
     Kur
    0.65
    NewReader
    0.61
    Kur
    0.58
    AspNetCore
    0.58
     deme
    0.57
     Preferencias
    0.57
     spray
    0.57
    Activations Density 0.180%

    No Known Activations