© 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. 19-GEMMASCOPE-RES-16K
    6. 622
    Prev
    Next
    INDEX
    Explanations

    terms related to specificity and relational properties in various contexts

    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
    xsi
    -0.44
    而已
    -0.43
    kuti
    -0.42
    tilli
    -0.42
    шено
    -0.41
    стол
    -0.36
    ntr
    -0.36
    aryana
    -0.35
    ophyta
    -0.35
    kura
    -0.34
    POSITIVE LOGITS
     both
    3.64
    both
    3.34
    Both
    2.97
     både
    2.83
     Both
    2.83
     zowel
    2.74
     sowohl
    2.62
    BOTH
    2.59
     zarówno
    2.58
     BOTH
    2.58
    Activations Density 1.141%

    No Known Activations