© 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. 9539
    Prev
    Next
    INDEX
    Explanations

    decision-making processes and expressions related to plans or intentions

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

    the verb "decided" followed by "to" and an action verb describing a deliberate choice or decision.

    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
     successfully
    -0.62
     successes
    -0.55
     successful
    -0.52
     succes
    -0.52
    successfully
    -0.51
     Successfully
    -0.50
     успе
    -0.49
     موفق
    -0.49
     rius
    -0.49
    Erfolge
    -0.48
    POSITIVE LOGITS
     pursue
    0.63
     propOrder
    0.58
     quit
    0.56
     pursuing
    0.56
     Quit
    0.54
     ditch
    0.53
     quitting
    0.52
    Quit
    0.52
     QUIT
    0.51
     skip
    0.49
    Activations Density 0.675%

    No Known Activations