Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14724
    Prev
    Next
    INDEX
    Explanations

    references to money, finances, and distribution of resources

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

    Code, signatures, and program instructions

    np_acts-logits-general · gemini-2.0-flash

    by class, insert, signer, another, fold, large

    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
    //
    -0.63
     hiç
    -0.57
    WithMany
    -0.53
    WebVitals
    -0.53
     invokingState
    -0.52
     اصلا
    -0.50
     >=",
    -0.50
     ningún
    -0.49
     ogóle
    -0.48
    AsyncResult
    -0.47
    POSITIVE LOGITS
     individually
    1.25
     separately
    1.21
     einzeln
    1.15
     câte
    1.15
    마
    0.88
     independently
    0.88
    씩
    0.86
     ayrı
    0.84
    individ
    0.80
    ごとに
    0.79
    Activations Density 0.280%

    No Known Activations