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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11084
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in the document layout

    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
    __':
    
    -0.90
    ValueStyle
    -0.76
     nahilalakip
    -0.73
    |}{$
    -0.73
    Hentet
    -0.72
    RunAsync
    -0.71
    StoryboardSegue
    -0.70
     Administrativna
    -0.68
     aard
    -0.68
     thal
    -0.65
    POSITIVE LOGITS
    Bronnen
    0.62
    override
    0.59
     Barbier
    0.50
     كومونز
    0.50
    jednoc
    0.50
     judged
    0.50
    iParam
    0.49
     }^{\
    0.48
     obstante
    0.47
     særlig
    0.47
    Activations Density 0.254%

    No Known Activations