© 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. 16130
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and conjunctions in the text

    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
     purpoſe
    -0.76
     beſt
    -0.72
     leſs
    -0.72
     fubject
    -0.71
     ſtre
    -0.70
     laſt
    -0.70
     ſte
    -0.70
     myſelf
    -0.69
     ſeveral
    -0.69
     theſe
    -0.68
    POSITIVE LOGITS
     And
    1.64
     AND
    1.48
     and
    1.42
     và
    1.42
    And
    1.39
    and
    1.32
     и
    1.30
     και
    1.25
    และ
    1.12
     \&
    1.11
    Activations Density 0.102%

    No Known Activations