Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 399
    Prev
    Next
    INDEX
    Explanations

    key phrases related to conditional scenarios and comparisons

    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
    RectangleBorder
    -0.64
    sprechend
    -0.58
    modb
    -0.55
    archiviato
    -0.53
    GOTREF
    -0.51
    expandindo
    -0.50
    WebControls
    -0.48
    TintMode
    -0.48
     <=",
    -0.48
     BorderSide
    -0.47
    POSITIVE LOGITS
     without
    3.30
     Without
    2.98
    without
    2.97
    Without
    2.93
     WITHOUT
    2.60
     zonder
    2.50
     ohne
    2.48
    WITHOUT
    2.43
     tanpa
    2.41
     senza
    2.35
    Activations Density 0.894%

    No Known Activations