© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 6457
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting characters in a document

    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
    chus
    -0.43
     bugs
    -0.38
    selective
    -0.38
     Atenas
    -0.37
    XXXXXX
    -0.36
     balance
    -0.36
    маны
    -0.36
    rawDesc
    -0.36
    #'
    -0.35
    viaf
    -0.35
    POSITIVE LOGITS
    ########.
    1.03
    ⓧ
    0.87
     يتيمه
    0.86
    TintMode
    0.86
     disponibilités
    0.85
    ніципа
    0.83
    帖最后由
    0.82
     كومونز
    0.82
    WithIOException
    0.78
    脚注の使い方
    0.78
    Activations Density 0.250%

    No Known Activations