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. 13-GEMMASCOPE-RES-16K
    6. 37
    Prev
    Next
    INDEX
    Explanations

    phrases related to confirming actions or assertions

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

    Russian and Czech verbs related to making or doing actions, especially in infinitive forms.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constantly
    -0.64
    Everyday
    -0.56
    Portail
    -0.56
    ніципа
    -0.54
     often
    -0.54
     Aps
    -0.53
    parsedMessage
    -0.52
    ándote
    -0.52
    böz
    -0.51
     frequently
    -0.50
    POSITIVE LOGITS
    脚注の使い方
    0.89
    RTLR
    0.85
    imek
    0.80
    Hozzáférés
    0.77
    .*")]
    0.73
    consulté
    0.71
     pronoun
    0.71
    themselves
    0.71
    onedDateTime
    0.71
     HomeComponent
    0.69
    Activations Density 0.030%

    No Known Activations