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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6467
    Prev
    Next
    INDEX
    Explanations

    references to "pit" or "Pit" 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 @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.64
    AxisAlignment
    -0.60
    yntaxException
    -0.59
     ilç
    -0.59
     Lange
    -0.56
    entos
    -0.55
    RDP
    -0.55
    ogni
    -0.53
     Agency
    -0.52
     PIO
    -0.52
    POSITIVE LOGITS
    OGND
    0.73
     صوتيه
    0.71
     Roskov
    0.64
    endpush
    0.63
    styleable
    0.63
     utafitiHapana
    0.63
     Мексичка
    0.60
     protoimpl
    0.60
     समीक्षाओं
    0.58
    AfterClass
    0.57
    Activations Density 0.125%

    No Known Activations