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. 22-GEMMASCOPE-RES-16K
    6. 11103
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific concepts and discussions

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

    Location or state of being

    np_acts-logits-general · gemini-2.0-flash

    being located or contained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.88
    MigrationBuilder
    -0.69
    IndentedString
    -0.61
    下载附件
    -0.59
     ویکی‌پدیا
    -0.58
    awaiter
    -0.56
     يتيمه
    -0.54
    fjspx
    -0.54
     bezeichneter
    -0.54
    withIdentifier
    -0.53
    POSITIVE LOGITS
     located
    1.76
     situated
    1.47
     housed
    1.46
     contained
    1.40
     residing
    1.36
    located
    1.33
     Located
    1.31
    Located
    1.22
     embedded
    1.19
     nestled
    1.17
    Activations Density 0.968%

    No Known Activations