© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 9685
    Prev
    Next
    INDEX
    Explanations

    instances of the word "complain" and its variants

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

    complaining about something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     виправивши
    -0.57
    TemporalType
    -0.53
     kaarangay
    -0.50
    GenerationType
    -0.47
    WireFormatLite
    -0.46
    цездатний
    -0.45
     snippetHide
    -0.45
     Wikimedijinoj
    -0.44
    Autoritní
    -0.44
    幸いです
    -0.43
    POSITIVE LOGITS
     about
    0.72
     bitterly
    0.69
     يتيمه
    0.61
     loudly
    0.59
     loud
    0.58
     loudest
    0.56
    loud
    0.54
    PARTMENT
    0.52
     tungkol
    0.52
     louder
    0.51
    Activations Density 0.011%

    No Known Activations