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. 725
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and functions associated with HTTP requests and responses

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

    Code related to API responses/requests

    np_acts-logits-general · gemini-2.0-flash

    Go code structures

    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
    MemoryWarning
    -0.63
     onCreateView
    -0.62
    ReusableCell
    -0.61
    IVEREF
    -0.59
    JsonInclude
    -0.59
    saraba
    -0.57
     Dostupné
    -0.57
    WireFormat
    -0.56
    terase
    -0.55
    Obrázky
    -0.55
    POSITIVE LOGITS
    Chham
    0.61
    tvrt
    0.52
    Fren
    0.51
     XCTest
    0.48
     continúas
    0.46
    şekkür
    0.44
    requestCode
    0.44
    ">//
    0.43
    >",
    
    0.43
    :],
    0.42
    Activations Density 0.145%

    No Known Activations