© 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. 5869
    Prev
    Next
    INDEX
    Explanations

    contexts involving a systemic or comprehensive approach to treatment and medical circumstances

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

    after technical terms or proper nouns

    np_acts-logits-general · gemini-2.0-flash

    following prepositions

    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
     Савезне
    -1.34
    ſelves
    -1.34
    ſelf
    -1.30
     Roskov
    -1.22
     Majefty
    -1.13
     pleaſure
    -1.13
     purpoſe
    -1.11
    GraphicsUnit
    -1.10
     autorytatywna
    -1.07
    WithIOException
    -1.07
    POSITIVE LOGITS
     […]
    1.43
     …
    1.19
    <eos>
    1.16
    […]
    1.06
    …
    1.03
    ,…
    0.91
     [...]
    0.88
    .…
    0.85
    ….
    0.83
     ...
    0.81
    Activations Density 2.431%

    No Known Activations