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. 5-GEMMASCOPE-RES-16K
    6. 9080
    Prev
    Next
    INDEX
    Explanations

    verbs associated with pulling or dragging actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    سطس
    -0.58
    Ware
    -0.53
     Ware
    -0.51
    textTheme
    -0.50
     onItemClick
    -0.49
    afp
    -0.48
    spricht
    -0.47
     Bam
    -0.46
     đa
    -0.46
    nologi
    -0.45
    POSITIVE LOGITS
     pulled
    1.52
     Pulling
    1.51
     pulls
    1.44
     drawn
    1.44
    pulled
    1.44
    pull
    1.43
     pull
    1.42
     Pulled
    1.41
     pulling
    1.41
     Drawn
    1.40
    Activations Density 0.195%

    No Known Activations