© 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. 40-GEMMASCOPE-RES-16K
    11. 1998
    Prev
    Next
    INDEX
    Explanations

    words related to modal verbs and their usage in hypothetical or conditional situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moeite
    -0.55
     sentimenti
    -0.49
     række
    -0.47
     appunt
    -0.46
     wyboru
    -0.46
     gemakkelijk
    -0.45
     makkelijk
    -0.45
     vantaggi
    -0.45
     rapporti
    -0.45
     plezier
    -0.44
    POSITIVE LOGITS
    ########.
    0.40
     statis
    0.40
     cooler
    0.38
     MainAxisSize
    0.36
     tech
    0.36
    NSIndexPath
    0.36
    ärzt
    0.35
    amerikanischer
    0.35
     fairer
    0.35
     planches
    0.35
    Activations Density 0.182%

    No Known Activations