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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 3027
    Prev
    Next
    INDEX
    Explanations

    responses indicating problem-solving or solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related questions and answers

    np_acts-logits-general · gemini-2.0-flash

    I think or just declare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WarningLevel
    -0.59
    ')))
    -0.56
    }))
    -0.49
    Virgo
    -0.48
    ']))
    -0.48
    })$,
    -0.47
    idi
    -0.46
    ]))
    
    -0.46
    ara
    -0.46
    jLabel
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    0.79
    extAlignment
    0.64
     encontrou
    0.60
    sizeCache
    0.59
     yder
    0.58
     ModelExpression
    0.57
    AsUp
    0.56
    solved
    0.54
     AssemblyCulture
    0.54
     løs
    0.54
    Activations Density 0.128%

    No Known Activations