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. 5-GEMMASCOPE-RES-16K
    6. 10530
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and their frequency in the text

    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
     préférence
    -0.52
    NameInMap
    -0.51
    names
    -0.50
    houses
    -0.49
    řen
    -0.47
    house
    -0.45
     Савезне
    -0.45
     thingy
    -0.44
    Harm
    -0.44
     Mühe
    -0.43
    POSITIVE LOGITS
    encodeWith
    0.71
    ToAction
    0.69
    MLLoader
    0.68
    UIControlState
    0.67
    }))
    
    0.65
    httphttps
    0.65
     useCallback
    0.65
     ujednoznacz
    0.64
    BindingResult
    0.61
    AutoresizingMask
    0.60
    Activations Density 0.396%

    No Known Activations