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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 8312
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "with" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -1.10
     a
    -0.91
     both
    -0.81
     an
    -0.79
     either
    -0.78
     any
    -0.73
    ]),
    
    -0.71
     some
    -0.70
     multiple
    -0.69
     anything
    -0.69
    POSITIVE LOGITS
    DeleteBehavior
    0.60
    webElementXpaths
    0.59
     noires
    0.58
     disambiguazione
    0.58
     propOrder
    0.57
     vectorielles
    0.56
     linkovi
    0.53
     hasbro
    0.53
    ंदीखरीदारी
    0.51
    ungguhnya
    0.51
    Activations Density 0.118%

    No Known Activations