© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 678
    Prev
    Next
    INDEX
    Explanations

    statements expressing a preference for alarming or negative outcomes

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

    rather X than Y structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.47
     modelAndView
    -0.43
     itemprop
    -0.40
     endfor
    -0.38
    ungsver
    -0.38
     cherchés
    -0.37
    PerformLayout
    -0.37
    getSystemService
    -0.36
    RegistryLite
    -0.36
    CardBody
    -0.35
    POSITIVE LOGITS
     than
    0.62
    Than
    0.62
     decât
    0.56
    Rather
    0.53
     THAN
    0.53
    than
    0.52
     liever
    0.51
     než
    0.50
     niż
    0.48
     autorytatywna
    0.47
    Activations Density 0.021%

    No Known Activations