© 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. 20-GEMMASCOPE-RES-16K
    6. 11326
    Prev
    Next
    INDEX
    Explanations

    academic papers and studies discussing specific research works

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

    "In this study" or "In this paper"

    np_acts-logits-general · gemini-2.0-flash

    in this paper we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -1.06
     betweenstory
    -0.96
     насељу
    -0.91
     Administrativna
    -0.88
    ConstraintMaker
    -0.88
    oredCriteria
    -0.87
    OGND
    -0.86
    хьтан
    -0.85
    MLLoader
    -0.84
    protoimpl
    -0.83
    POSITIVE LOGITS
     we
    0.87
     you
    0.72
    不但
    0.68
    Instead
    0.67
     علاوه
    0.63
     instead
    0.61
     emphasis
    0.60
     Instead
    0.60
    instead
    0.59
     besides
    0.57
    Activations Density 0.464%

    No Known Activations