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. 16-GEMMASCOPE-RES-16K
    6. 8913
    Prev
    Next
    INDEX
    Explanations

    technical terms related to database operations and optimization

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

    Non-English language snippets

    np_acts-logits-general · gemini-2.0-flash

    backup and restore operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -0.55
     and
    -0.52
    **
    -0.51
    المكان
    -0.50
    *}
    -0.46
    *}$
    -0.45
    testens
    -0.45
     
    -0.45
    ;}
    -0.44
     late
    -0.44
    POSITIVE LOGITS
     الحره
    0.80
     بيها
    0.77
    出版年
    0.74
    GraphicsUnit
    0.72
    EndInit
    0.69
    rentices
    0.68
    Hentet
    0.67
    seamnă
    0.66
     كومونز
    0.66
     fibrillation
    0.65
    Activations Density 0.066%

    No Known Activations