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. 720
    Prev
    Next
    INDEX
    Explanations

    individuals associated with various sports teams or athletic activities

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

    First names followed by last initials

    np_acts-logits-general · gemini-2.0-flash

    athlete first names and surnames

    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
     صوتيه
    -0.90
     Paglinawan
    -0.84
     snippetHide
    -0.83
    ⓧ
    -0.77
    tagHelperRunner
    -0.71
     pinulongan
    -0.71
    ValueStyle
    -0.69
     Majefty
    -0.68
     CreateTagHelper
    -0.67
     Cæsar
    -0.66
    POSITIVE LOGITS
     Fre
    0.46
    ">>
    0.45
     Ad
    0.44
    djangoproject
    0.44
    )$}
    0.43
    adə
    0.43
     Sch
    0.43
     Admit
    0.43
    CUSSION
    0.43
     admiti
    0.43
    Activations Density 0.108%

    No Known Activations