© 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. 2-GEMMASCOPE-RES-16K
    11. 2345
    Prev
    Next
    INDEX
    Explanations

    expressions indicating clarity or certainty

    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
     GenerationType
    -0.77
    sidemargin
    -0.56
     Paxton
    -0.56
    dess
    -0.56
     Arm
    -0.55
    oult
    -0.55
     Bevan
    -0.55
     PRACTICES
    -0.54
     Lovell
    -0.54
    intersect
    -0.54
    POSITIVE LOGITS
     clearly
    3.50
    clearly
    3.23
     Clearly
    3.01
    Clearly
    2.83
     claramente
    2.48
     clairement
    2.29
     chiaramente
    2.25
     duidelijk
    1.95
     plainly
    1.88
     CLEAR
    1.73
    Activations Density 0.094%

    No Known Activations