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. 984
    Prev
    Next
    INDEX
    Explanations

    pronouns and specific verbs indicating personal connections or feelings

    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
     Efq
    -1.41
     Majefty
    -1.32
    ſelf
    -1.31
     myſelf
    -1.30
     Monfieur
    -1.29
     himſelf
    -1.21
     Jefus
    -1.19
     houſe
    -1.17
     pleaſure
    -1.16
     itſelf
    -1.14
    POSITIVE LOGITS
     hence
    0.79
     therefore
    0.71
     استنادى
    0.61
     I
    0.61
    hence
    0.60
     consequently
    0.60
    </i>
    0.59
     zwar
    0.58
    </b>
    0.58
    NullCheck
    0.57
    Activations Density 0.244%

    No Known Activations