© 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. 24-GEMMASCOPE-RES-16K
    11. 1407
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to mechanical engineering and manufacturing processes

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

    preceding a requirement or desire

    np_acts-logits-general · gemini-2.0-flash

    need or necessity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.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
    Vidite
    -0.47
     Italijanski
    -0.43
    adpleegd
    -0.38
    湃
    -0.37
    AutoField
    -0.36
     ObjectParameter
    -0.34
    DebuggerNonUser
    -0.34
    chan
    -0.34
    تفصیلات
    -0.34
    ыгана
    -0.33
    POSITIVE LOGITS
     potrzeb
    0.71
     needs
    0.71
     needing
    0.70
     kebutuhan
    0.70
     need
    0.69
     Needs
    0.68
    的需求
    0.68
     potrzeby
    0.67
     esigenze
    0.67
    Need
    0.66
    Activations Density 0.757%

    No Known Activations