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. 12-GEMMASCOPE-RES-16K
    6. 12379
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and contractions, indicating a focus on individual perspectives and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ‘
    -1.53
     “
    -1.52
    ’
    -1.33
    ”
    -1.28
    .’
    -1.26
    ’,
    -1.26
    ’.
    -1.25
    =”
    -1.24
    .”
    -1.19
    ,’
    -1.13
    POSITIVE LOGITS
     Jefus
    1.38
     purpoſe
    1.37
     poffible
    1.30
     Efq
    1.30
     ainfi
    1.29
     ſtate
    1.28
     Majefty
    1.26
     againſt
    1.24
     houſe
    1.23
     myſelf
    1.22
    Activations Density 0.602%

    No Known Activations