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. 3-GEMMASCOPE-RES-16K
    6. 9852
    Prev
    Next
    INDEX
    Explanations

    mentions of "adventure" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arket
    -0.69
     endforeach
    -0.58
    خرى
    -0.58
     Ramsay
    -0.58
     Kett
    -0.56
     públicos
    -0.56
    {$
    -0.54
     balk
    -0.54
    getitem
    -0.53
    ゴリー
    -0.51
    POSITIVE LOGITS
     adventure
    1.82
     Adventure
    1.66
     adventures
    1.58
    Adventure
    1.58
    adventure
    1.48
     Adventures
    1.38
     ADVENT
    1.31
    Adventures
    1.19
     aventure
    1.16
    adventures
    1.14
    Activations Density 0.059%

    No Known Activations