© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 11921
    Prev
    Next
    INDEX
    Explanations

    elements related to decision-making and evaluation of quality

    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
    styleType
    -0.75
    ForValue
    -0.58
    rungsseite
    -0.56
    NameInMap
    -0.54
    antMatchers
    -0.53
    setVerticalGroup
    -0.51
     conséquence
    -0.50
    цездатний
    -0.50
    jgl
    -0.50
    FunctionFlags
    -0.50
    POSITIVE LOGITS
     because
    2.26
    because
    1.92
     porque
    1.90
    Because
    1.78
     Because
    1.76
     perché
    1.65
     karena
    1.61
    因为
    1.60
     Çünkü
    1.57
     BECAUSE
    1.57
    Activations Density 1.038%

    No Known Activations