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. 8-GEMMASCOPE-RES-16K
    6. 5700
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in code or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -1.31
    LookAnd
    -1.13
     Мексичка
    -1.12
    تقاوى
    -1.10
     unknownFields
    -1.09
     oprot
    -1.09
    localctx
    -1.07
     itſelf
    -1.05
    SharedDtor
    -1.04
    IVEREF
    -1.03
    POSITIVE LOGITS
     “
    0.57
    “
    0.52
    <h6>
    0.52
    <strong>
    0.51
    <td>
    0.50
    <b>
    0.49
     ‘
    0.48
    「
    0.48
    The
    0.47
    <h2>
    0.47
    Activations Density 0.510%

    No Known Activations