© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8504
    Prev
    Next
    INDEX
    Explanations

    phrases related to ratings or evaluations

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

    Followed by punctuation or quotes

    np_acts-logits-general · gemini-2.0-flash

    scared silly, manager, code, 8 bp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.94
    awtextra
    -0.80
     CreateTagHelper
    -0.79
    Datuak
    -0.75
    Personendaten
    -0.73
     للمعارف
    -0.73
    LLocation
    -0.68
    libft
    -0.67
    AccessorTable
    -0.66
    تقاوى
    -0.65
    POSITIVE LOGITS
    Fuck
    0.58
     bastard
    0.54
    ~~
    0.53
     shit
    0.53
     fragrant
    0.52
     Brother
    0.52
     Lao
    0.52
     Fuck
    0.52
    ~~~
    0.52
     handsome
    0.52
    Activations Density 0.065%

    No Known Activations