© 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. 31-GEMMASCOPE-RES-16K
    11. 479
    Prev
    Next
    INDEX
    Explanations

    pronouns and auxiliary verbs that indicate personal engagement or perspective

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

    the conditional phrase structure "you could/would/can/could be."

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gynnwys
    -0.47
     bluzka
    -0.45
     myſelf
    -0.44
     étoit
    -0.39
     ſever
    -0.39
     ſtre
    -0.39
     koszulka
    -0.39
     themſelves
    -0.38
    незон
    -0.37
    horabuena
    -0.37
    POSITIVE LOGITS
    ########.
    0.67
    AndEndTag
    0.62
     rarely
    0.60
     seldom
    0.58
     hear
    0.55
     gotta
    0.53
     hears
    0.52
    MessageOf
    0.51
     snippetHide
    0.51
     expect
    0.50
    Activations Density 0.206%

    No Known Activations