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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 10575
    Prev
    Next
    INDEX
    Explanations

    phrases that describe varying frequency and condition of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.79
    ladel
    -0.60
    MLLoader
    -0.59
    __":
    -0.58
    VersionUID
    -0.57
    TargetException
    -0.56
    satunya
    -0.56
     Vikipedi
    -0.55
    __":
    
    -0.55
     Audiodateien
    -0.54
    POSITIVE LOGITS
     basis
    1.60
    basis
    1.29
     Basis
    1.26
    Basis
    1.19
     bases
    1.09
     BASIS
    1.08
     basi
    0.85
    bases
    0.84
     Bases
    0.83
    Bases
    0.82
    Activations Density 0.144%

    No Known Activations