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. 3-GEMMASCOPE-RES-16K
    6. 10875
    Prev
    Next
    INDEX
    Explanations

    phrases that involve ownership or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    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
    -0.81
     Majefty
    -0.76
     chofe
    -0.72
     myſelf
    -0.70
     ſtate
    -0.69
     Eſ
    -0.67
     ſtre
    -0.67
     juſ
    -0.65
     houſe
    -0.64
     diſt
    -0.64
    POSITIVE LOGITS
     surla
    0.66
    |}{$
    0.63
    说起
    0.59
     ['$
    0.57
     discusses
    0.57
    cussed
    0.54
    揄
    0.53
     KeyEvent
    0.52
    ocardio
    0.52
    AnimationFrame
    0.51
    Activations Density 0.140%

    No Known Activations