© 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. 18-GEMMASCOPE-RES-16K
    6. 6844
    Prev
    Next
    INDEX
    Explanations

    references to experimental results and methodologies in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Filenames or URLs with hyphens and extensions

    np_acts-logits-general · gemini-2.0-flash

    figure references and table references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Przypisy
    -0.57
    Джерела
    -0.54
     isSet
    -0.52
    theguardian
    -0.48
    Izvori
    -0.48
     MonoBehaviour
    -0.48
    culum
    -0.45
     iconLine
    -0.45
     للمعارف
    -0.45
    Geschiedenis
    -0.44
    POSITIVE LOGITS
    ]='\
    0.68
     autorytatywna
    0.65
    "]);
    
    0.65
    :✨
    0.62
     nahilalakip
    0.61
    Personendaten
    0.58
    )");
    
    0.57
     magnétique
    0.57
    >);
    0.56
     &___
    0.54
    Activations Density 0.366%

    No Known Activations