© 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. 2-GEMMASCOPE-RES-16K
    6. 6979
    Prev
    Next
    INDEX
    Explanations

    occurrences of articles such as "a" and "an" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.61
    <bos>
    -0.55
     immédi
    -0.52
     kohta
    -0.50
     चीज़ों
    -0.50
     chamada
    -0.49
     Gubernur
    -0.49
     égal
    -0.49
     iprot
    -0.49
    enação
    -0.48
    POSITIVE LOGITS
    Espèce
    0.63
     CURIAM
    0.61
    __*/
    0.58
    
    0.56
    onAttach
    0.55
    rxjs
    0.54
    ERICAL
    0.53
    endphp
    0.53
    Wird
    0.53
    ohist
    0.53
    Activations Density 0.328%

    No Known Activations