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. 4-GEMMASCOPE-RES-16K
    6. 12165
    Prev
    Next
    INDEX
    Explanations

    references to hanging or suspension, particularly involving necks or similar contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexType
    -0.67
    orsese
    -0.65
    PageIndex
    -0.65
    pielt
    -0.62
    UnitTesting
    -0.61
    期刊论文
    -0.60
     enco
    -0.57
    PreExecute
    -0.56
     dandelion
    -0.56
     propTypes
    -0.56
    POSITIVE LOGITS
     hang
    2.17
     hanging
    2.08
     hangs
    2.04
     hung
    2.00
     Hang
    1.93
    hanging
    1.91
    Hanging
    1.90
     Hanging
    1.86
     HANG
    1.85
    Hang
    1.75
    Activations Density 0.172%

    No Known Activations