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. 4437
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to arguments or claims being made in a debate or discussion

    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
    djangoproject
    -0.87
    netbeans
    -0.59
    MutableLiveData
    -0.58
    CompilerServices
    -0.55
    ocities
    -0.55
    CodeAttribute
    -0.53
     ComVisible
    -0.53
     biết
    -0.52
     kasarigan
    -0.52
     ternyata
    -0.51
    POSITIVE LOGITS
     argue
    1.61
     argued
    1.56
     argues
    1.54
     arguing
    1.41
     arguments
    1.31
     Arguments
    1.31
     argument
    1.22
     argumenta
    1.19
     argu
    1.18
    argue
    1.15
    Activations Density 0.268%

    No Known Activations