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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5152
    Prev
    Next
    INDEX
    Explanations

    words that indicate essential qualities or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caron
    -0.59
    SerializeField
    -0.59
     Warte
    -0.59
     imposition
    -0.58
    Donovan
    -0.58
    flich
    -0.57
    manan
    -0.57
    حياتها
    -0.57
     sight
    -0.56
    zyden
    -0.56
    POSITIVE LOGITS
     essentially
    2.51
    Essentially
    2.40
    essentially
    2.39
     basically
    2.37
     Essentially
    2.33
    Basically
    2.23
    basically
    2.20
     Basically
    2.15
     básicamente
    1.88
     essentiellement
    1.42
    Activations Density 0.141%

    No Known Activations