© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80475
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or contrasts between two sides or aspects, particularly using the phrase "on one hand" and related expressions

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

    on one hand and the other

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     bulunabilir
    -0.36
    Hozzáférés
    -0.35
    Flip
    -0.32
     Vig
    -0.31
    ถึง
    -0.31
    Ծանոթ
    -0.30
    Péri
    -0.30
     hop
    -0.29
    ập
    -0.29
     Sched
    -0.29
    POSITIVE LOGITS
    enterOuterAlt
    0.71
    oredCriteria
    0.60
     ligiloj
    0.60
    +#+
    0.58
    Autoritní
    0.53
     мәкал
    0.53
    ThroughAttribute
    0.52
    internalType
    0.51
    ItemBackground
    0.50
    styleType
    0.50
    Activations Density 0.163%

    No Known Activations