© 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
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11109
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" associated with various contexts, indicating discussions around locations, conditions, and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     instead
    -0.37
    instead
    -0.32
    preferably
    -0.32
     вместо
    -0.32
     preferably
    -0.32
     or
    -0.30
    ientôt
    -0.29
    代わりに
    -0.29
     feil
    -0.29
     замі
    -0.29
    POSITIVE LOGITS
     terms
    1.32
     regards
    1.17
    terms
    1.02
     regard
    0.98
    regards
    0.93
     Hinsicht
    0.92
     Hinblick
    0.89
     cuanto
    0.86
     términos
    0.85
     плане
    0.82
    Activations Density 0.496%

    No Known Activations