© 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. 3-GEMMASCOPE-RES-16K
    11. 13045
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a summary or restatement of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     einzeln
    -0.62
     DHS
    -0.57
    曾在
    -0.56
     Clifton
    -0.56
     oficio
    -0.56
     Astor
    -0.55
    ్రామ
    -0.55
     comor
    -0.54
     selectivity
    -0.54
     publice
    -0.54
    POSITIVE LOGITS
     basically
    2.63
     essentially
    2.56
    essentially
    2.49
    basically
    2.48
    Basically
    2.48
    Essentially
    2.46
     Essentially
    2.44
     Basically
    2.40
     básicamente
    1.81
     practically
    1.32
    Activations Density 0.058%

    No Known Activations