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. 12-GEMMASCOPE-RES-16K__L0-22
    6. 81
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 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
    )))));
    -0.80
    UnsafeEnabled
    -0.76
    MENAFN
    -0.73
    ())));
    -0.70
    ंदीखरीदारी
    -0.68
    ]}"
    -0.66
    ChildScrollView
    -0.66
     saites
    -0.66
     kasarigan
    -0.65
     ISNI
    -0.63
    POSITIVE LOGITS
     (
    0.51
    SequentialGroup
    0.49
     Familienname
    0.48
    Aktualisiert
    0.46
    ,
    0.44
    plasia
    0.44
    SceneManagement
    0.44
    μως
    0.43
     fiasco
    0.43
    laten
    0.42
    Activations Density 0.138%

    No Known Activations