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. 25-GEMMASCOPE-RES-16K
    6. 1596
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and expressions of personal opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.71
     referenties
    -0.71
     فريبيس
    -0.58
     AspNetCore
    -0.57
    Smarty
    -0.55
     ơn
    -0.53
    ########.
    -0.53
     möge
    -0.53
     himo
    -0.51
     lenker
    -0.50
    POSITIVE LOGITS
     think
    2.22
     thinks
    1.68
    think
    1.62
     Think
    1.43
    Think
    1.39
     THINK
    1.28
     believe
    1.11
     thin
    1.06
    THINK
    1.04
     thing
    1.03
    Activations Density 0.409%

    No Known Activations