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. 8561
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes involving detection and monitoring in various contexts

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

    Chain or path in a system

    np_acts-logits-general · gemini-2.0-flash

    progress along a chain or path

    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
     disambiguazione
    -0.64
    RetentionPolicy
    -0.63
    apunov
    -0.58
     GetEnumerator
    -0.55
     Scroll
    -0.54
     pinulongan
    -0.54
    SharedCtor
    -0.54
    ++);
    -0.52
    scroll
    -0.52
     scrolling
    -0.50
    POSITIVE LOGITS
     chain
    1.10
     stages
    0.99
     downstream
    0.97
    Chain
    0.94
     Chain
    0.93
     upstream
    0.92
    环节
    0.92
     steps
    0.91
    chain
    0.89
     chaîne
    0.81
    Activations Density 0.524%

    No Known Activations