Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-GEMMASCOPE-RES-16K
    6. 5744
    Prev
    Next
    INDEX
    Explanations

    concepts related to community involvement and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    väg
    -0.49
    gameserver
    -0.47
    Synonymes
    -0.46
    ⓧ
    -0.46
     bewer
    -0.46
    いくつか
    -0.45
     isso
    -0.44
    適当
    -0.44
    Tē
    -0.43
    ưng
    -0.43
    POSITIVE LOGITS
     others
    1.39
     everyone
    1.28
    everyone
    1.12
     everybody
    1.08
    others
    1.07
     humankind
    1.06
     mankind
    1.05
     anyone
    0.99
     millions
    0.96
     generations
    0.93
    Activations Density 0.444%

    No Known Activations