© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 93186
    Prev
    Next
    INDEX
    Explanations

    topics related to financial struggles and their impact on individuals and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     nakalista
    -0.61
    LookAnd
    -0.56
    AndEndTag
    -0.54
    WithIOException
    -0.49
     EconPapers
    -0.48
    出版年
    -0.46
     مشين
    -0.45
     NavController
    -0.44
    reactstrap
    -0.42
    IContainer
    -0.42
    POSITIVE LOGITS
    arangay
    0.50
     avoient
    0.46
     auroit
    0.41
     feroit
    0.41
    KindOfClass
    0.41
     étoient
    0.40
     pouvoit
    0.39
     privilégi
    0.39
     étoit
    0.38
     Einfluß
    0.38
    Activations Density 0.039%

    No Known Activations