© 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. 6679
    Prev
    Next
    INDEX
    Explanations

    terms related to persistence and consistency in programming and data structures

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

    ending in "yn", "ency", "ion", "lage", or "sistency"

    np_acts-logits-general · gemini-2.0-flash

    persistency service

    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
     ainfi
    -0.92
     anún
    -0.91
     propOrder
    -0.80
    alakip
    -0.79
    arangay
    -0.78
    attutto
    -0.77
    berdayakan
    -0.77
    pecabe
    -0.77
    ambién
    -0.75
     pérd
    -0.74
    POSITIVE LOGITS
    Leary
    0.58
    躇
    0.54
    ers
    0.53
    ment
    0.49
    Donnell
    0.48
    AxisAlignment
    0.48
    zzleHttp
    0.47
    al
    0.46
    </sup>
    0.46
    or
    0.46
    Activations Density 3.295%

    No Known Activations