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. 22-GEMMASCOPE-RES-16K
    6. 5896
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to probabilities and efficiencies in a structured, formulaic context

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

    Mathematical notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RunWith
    -0.60
     فريبيس
    -0.55
    andExpect
    -0.51
     InkWell
    -0.50
    InputBorder
    -0.50
    gridx
    -0.49
    ercito
    -0.47
    "]="
    -0.45
     المعيارى
    -0.45
    ்த்த
    -0.44
    POSITIVE LOGITS
     lenker
    0.75
     Privacidade
    0.60
    قایناق‌لار
    0.60
    
    0.59
    ViewImports
    0.59
    তথ্যসূত্র
    0.58
    toMatchSnapshot
    0.58
    /*
    0.58
    حوالہ
    0.56
     odkazy
    0.56
    Activations Density 0.092%

    No Known Activations