© 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. 16-GEMMASCOPE-RES-16K
    6. 3469
    Prev
    Next
    INDEX
    Explanations

    the word "Another" and its variants, indicating repetitions or additional items in a list or context

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

    "Another" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    another followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cubs
    -0.65
     docx
    -0.65
     SPS
    -0.62
     Lyme
    -0.61
     Utilisez
    -0.60
     guilds
    -0.60
     studs
    -0.59
     rhiz
    -0.59
     copii
    -0.59
     hoes
    -0.56
    POSITIVE LOGITS
     }}"></
    0.95
    !("{}",
    0.95
    rungsseite
    0.82
    ])->
    0.82
     Another
    0.76
     dozen
    0.75
     another
    0.75
     AssemblyVersion
    0.75
     }}</
    0.74
    Another
    0.74
    Activations Density 0.052%

    No Known Activations