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. 15842
    Prev
    Next
    INDEX
    Explanations

    references to communication and requests for support or information

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

    Reported speech or indirect quotes using "said," "told," or "mentioned."

    np_acts-logits-general · gemini-2.0-flash

    reported speech

    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
    ponses
    -0.58
    deepcopy
    -0.49
     ब्रेकडाउन
    -0.46
    InnerText
    -0.45
    }))
    
    -0.45
    "])
    
    -0.45
     TextInputType
    -0.45
    ftagPool
    -0.43
    \@
    -0.43
    $.
    
    -0.42
    POSITIVE LOGITS
    LogFactory
    0.81
     مشين
    0.79
    StructEnd
    0.73
     könne
    0.70
    LEncoder
    0.70
    下载附件
    0.69
     hennes
    0.64
    로그램
    0.60
     müsse
    0.60
    HideFlags
    0.58
    Activations Density 0.158%

    No Known Activations