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. 12-GEMMASCOPE-RES-16K
    6. 5550
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations

    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
     Meksiku
    -0.53
    ISupport
    -0.52
    )))),
    -0.50
    BeginInit
    -0.49
    rch
    -0.47
    gu
    -0.47
    toHaveBeenCalled
    -0.45
    StoryboardSegue
    -0.45
     Bek
    -0.45
     AM
    -0.45
    POSITIVE LOGITS
     pleaſure
    0.70
     utafitiHapana
    0.67
     alimentaires
    0.65
    uxxxx
    0.64
    XmlAccessType
    0.63
    homonymie
    0.60
    AnimationsModule
    0.58
     Houſe
    0.58
     faſt
    0.57
     ſever
    0.57
    Activations Density 0.445%

    No Known Activations