© 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. 9-GEMMASCOPE-RES-131K
    11. 39010
    Prev
    Next
    INDEX
    Explanations

    references to various types of institutions

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

    public and private institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Egypte
    -0.60
    entrevista
    -0.56
     Polda
    -0.54
     RIPRODUZIONE
    -0.53
    eaway
    -0.50
    dry
    -0.49
    SourceChecksum
    -0.49
    Lead
    -0.49
     Gefahr
    -0.48
     Noruega
    -0.47
    POSITIVE LOGITS
     institutions
    1.84
     institution
    1.75
     Institutions
    1.72
     Institution
    1.64
    institution
    1.58
    institutions
    1.55
    Institution
    1.54
     INSTITUTION
    1.31
     institución
    1.27
     INSTIT
    1.17
    Activations Density 0.008%

    No Known Activations