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. 18-GEMMASCOPE-RES-16K
    6. 14553
    Prev
    Next
    INDEX
    Explanations

    references to mating systems and polygamy in relation to human evolution

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

    followed by "in" or "among"

    np_acts-logits-general · gemini-2.0-flash

    frequent among

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.60
     صوتيه
    -0.56
    webElementXpaths
    -0.56
    FormTagHelper
    -0.54
    Cyfeiriadau
    -0.51
    kháu
    -0.49
    MigrationBuilder
    -0.49
    Jeografia
    -0.48
     AssemblyCompany
    -0.47
    enné
    -0.46
    POSITIVE LOGITS
     among
    1.56
    among
    1.32
     amongst
    1.31
     chez
    1.27
     AMONG
    1.24
     Among
    1.22
     wśród
    1.13
    Among
    1.13
     Amongst
    1.02
     среди
    0.98
    Activations Density 0.846%

    No Known Activations