© 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. 0-GEMMASCOPE-RES-16K
    11. 8728
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "sub" and its variants in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    under
    -0.49
     under
    -0.44
     Under
    -0.41
     UNDER
    -0.39
    Under
    -0.39
    UNDER
    -0.38
    ConfigureAwait
    -0.36
    ExecutionContext
    -0.35
    耀
    -0.34
     McManus
    -0.34
    POSITIVE LOGITS
     subs
    2.91
     SUB
    2.83
     Sub
    2.83
    Sub
    2.75
     sub
    2.73
    SUB
    2.70
    sub
    2.58
     Subs
    2.52
    Subs
    2.38
    subs
    2.30
    Activations Density 0.204%

    No Known Activations