© 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. 37-GEMMASCOPE-RES-16K
    11. 4041
    Prev
    Next
    INDEX
    Explanations

    variations of the word "sub" and its forms in relation to urban environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     numberOfRows
    -0.43
    everywhere
    -0.40
    GEBURTS
    -0.40
    GEBURTSDATUM
    -0.39
    quiv
    -0.38
    yntaxException
    -0.37
     становника
    -0.37
    chyma
    -0.35
    nalités
    -0.35
    りに
    -0.35
    POSITIVE LOGITS
     sub
    0.73
    sub
    0.59
     Sub
    0.56
     getSub
    0.55
    Sub
    0.54
     <<<<<<<<<<<<<<
    0.53
    getSub
    0.52
    optimal
    0.48
    oxone
    0.47
    ramanian
    0.46
    Activations Density 0.194%

    No Known Activations