© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 4999
    Prev
    Next
    INDEX
    Explanations

    references to identifiers and protocols, particularly in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.81
    on
    -0.69
    pyplot
    -0.68
    S
    -0.67
    in
    -0.66
    (
    -0.66
    <strong>
    -0.65
    Pro
    -0.65
    Cap
    -0.64
    Trans
    -0.64
    POSITIVE LOGITS
     beginnetje
    1.01
    IsMutable
    0.97
     vPvB
    0.90
     propOrder
    0.90
     nélk
    0.89
    paravant
    0.88
    etheless
    0.88
    SharedCtor
    0.88
    
    0.87
     niega
    0.87
    Activations Density 0.843%

    No Known Activations