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. 14982
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data and related expressions

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

    Numbers and mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    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
     للاسماء
    -1.11
    Autoritní
    -0.79
    +#+#
    -0.71
     يتيمه
    -0.70
    FieldOffset
    -0.66
    RunWith
    -0.66
    Filmografie
    -0.65
    \{\\
    -0.63
     SIAM
    -0.63
    SOUNDBITE
    -0.63
    POSITIVE LOGITS
    脚注の使い方
    0.73
    addGap
    0.55
     sekal
    0.48
    agaimana
    0.42
     oprot
    0.40
     $^{
    0.40
     Коро
    0.40
    fitriones
    0.39
    Wię
    0.39
    oneofs
    0.39
    Activations Density 0.392%

    No Known Activations