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. 3555
    Prev
    Next
    INDEX
    Explanations

    measurements and dimensions in millimeters

    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
     Kome
    -0.59
    .​
    -0.56
     Stor
    -0.56
    ̀u
    -0.56
     Audiodateien
    -0.55
    pidou
    -0.54
     Kirch
    -0.54
    łod
    -0.53
     Kame
    -0.53
    û
    -0.53
    POSITIVE LOGITS
     mm
    2.27
    mm
    2.22
     мм
    1.61
     millimeters
    1.48
    MM
    1.47
     millimeter
    1.34
     MM
    1.34
     Mm
    1.24
    毫米
    1.18
    мм
    1.18
    Activations Density 0.083%

    No Known Activations