© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6768
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions involving family members and social dynamics

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

    Variables represented by single letters

    np_acts-logits-general · gemini-2.0-flash

    algebraic variables and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    tvguidetime
    -0.79
    WebElementEntity
    -0.59
    KommentareTeilen
    -0.58
    BeginContext
    -0.55
     nonUne
    -0.54
    RegressionTest
    -0.54
    AndEndTag
    -0.53
    +#+#
    -0.52
    nonatomic
    -0.51
    RTSN
    -0.50
    POSITIVE LOGITS
     OFDb
    0.35
    ナソニック
    0.35
     Normdatei
    0.35
     its
    0.34
     uska
    0.34
     prim
    0.33
    Gilla
    0.33
    Democrat
    0.33
     Democrat
    0.33
    メリ
    0.33
    Activations Density 0.615%

    No Known Activations