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. 15-GEMMASCOPE-RES-16K
    6. 1820
    Prev
    Next
    INDEX
    Explanations

    phrases that describe physical confrontations or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bit
    -0.43
    מעט
    -0.42
    АН
    -0.41
    SetBool
    -0.39
    стоян
    -0.39
    ctype
    -0.39
    Almost
    -0.38
    тистика
    -0.38
     tra
    -0.38
    总是
    -0.38
    POSITIVE LOGITS
     perhaps
    1.28
     maybe
    1.22
     possibly
    1.21
    perhaps
    1.19
     probably
    1.11
     Possibly
    1.10
    possibly
    1.07
     Probably
    1.06
    maybe
    1.04
     perchance
    1.04
    Activations Density 1.090%

    No Known Activations