© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4476
    Prev
    Next
    INDEX
    Explanations

    elements related to processes and functions in coding and algorithms

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

    Follows nouns/entities; "into" is a common subsequent preposition

    np_acts-logits-general · gemini-2.0-flash

    estimator, box, knife, facts, Array, bonds followed by directional words

    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
     nakalista
    -0.90
    :✨
    -0.81
    calaure
    -0.69
     يتيمه
    -0.68
     lenker
    -0.66
     continuant
    -0.66
    KommentareTeilen
    -0.65
    ])]
    -0.65
    }}],
    -0.65
     esternos
    -0.65
    POSITIVE LOGITS
     into
    0.85
     to
    0.55
     onto
    0.54
     away
    0.49
     against
    0.48
     INTO
    0.45
     unto
    0.43
    ไว้
    0.42
     over
    0.41
    into
    0.41
    Activations Density 0.669%

    No Known Activations