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. 13694
    Prev
    Next
    INDEX
    Explanations

    terms related to data security and research methodology

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

    technical or scientific details about physical objects and processes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    d
    -0.92
    k
    -0.91
    e
    -0.91
    m
    -0.87
    -
    -0.86
    n
    -0.85
    Slf
    -0.85
    p
    -0.84
    l
    -0.81
    u
    -0.80
    POSITIVE LOGITS
     myſelf
    1.84
     himſelf
    1.80
     themſelves
    1.79
     itſelf
    1.70
    ſelf
    1.60
    ſelves
    1.57
     ſeveral
    1.53
     whoſe
    1.51
     Majefty
    1.50
     Efq
    1.50
    Activations Density 8.271%

    No Known Activations