© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9060
    Prev
    Next
    INDEX
    Explanations

    declarations and definitions of data structures and variables in programming code

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

    Code syntax and punctuation

    np_acts-logits-general · gemini-2.0-flash

    code structure definitions

    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
    #+#
    -0.63
     disambiguazione
    -0.62
     verſch
    -0.57
    RegressionTest
    -0.57
    ロウィン
    -0.57
     laſſen
    -0.56
     ब्रेकडाउन
    -0.54
    oredCriteria
    -0.54
     cumplido
    -0.53
     pérd
    -0.53
    POSITIVE LOGITS
    ('/:
    0.39
    _
    0.33
    /*++
    0.32
    ('*',
    0.32
    ]').
    0.31
    Role
    0.30
     MonoBehaviour
    0.29
    ("/:
    0.29
    もちゃ
    0.29
    onete
    0.28
    Activations Density 0.504%

    No Known Activations