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. 3518
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inclusion or references to lists

    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
    label
    -0.49
    mės
    -0.49
    固
    -0.46
    for
    -0.45
      
    -0.45
     trebui
    -0.45
     -
    -0.44
    を受ける
    -0.44
    Governor
    -0.44
    http
    -0.44
    POSITIVE LOGITS
     AMONG
    1.25
     amongst
    1.10
     Amongst
    1.09
     Amid
    1.08
    among
    1.05
     amidst
    1.02
    Amid
    1.02
     among
    1.01
     amid
    0.98
    śród
    0.97
    Activations Density 0.253%

    No Known Activations