© 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. 18-GEMMASCOPE-RES-16K
    11. 8338
    Prev
    Next
    INDEX
    Explanations

    expressions summarizing or rephrasing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Phrases like "to put it [adverb]" or similar phrasing

    np_acts-logits-general · gemini-2.0-flash

    put it differently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnknownFieldSet
    -0.84
     Meksiku
    -0.83
    principalTable
    -0.83
     ролях
    -0.71
     fhew
    -0.71
    principalColumn
    -0.68
     EconPapers
    -0.65
     nakalista
    -0.65
     raiſ
    -0.65
     surla
    -0.65
    POSITIVE LOGITS
     put
    0.82
     Put
    0.72
    Put
    0.67
     autrement
    0.62
     inaczej
    0.60
     PUT
    0.60
    言い
    0.60
     way
    0.59
     ausged
    0.57
    put
    0.56
    Activations Density 0.167%

    No Known Activations