© 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. 2713
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making and comparisons between different options or scenarios

    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
     nid
    -0.54
    enough
    -0.53
     enough
    -0.52
    Enough
    -0.51
    ation
    -0.50
    izing
    -0.50
     Mazar
    -0.49
    %"),
    -0.49
    aturation
    -0.48
    ogonal
    -0.48
    POSITIVE LOGITS
     latter
    3.39
     former
    2.69
    latter
    2.40
    后者
    2.34
    former
    2.26
    Former
    2.20
     Former
    2.08
     senare
    1.81
     letz
    1.66
     later
    1.56
    Activations Density 0.496%

    No Known Activations