© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 87
    Prev
    Next
    INDEX
    Explanations

    references to organization and management in the context of teamwork and task delegation

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

    preceding verbs indicating possibility or necessity

    np_acts-logits-general · gemini-2.0-flash

    context setting descriptions

    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
    ChildIndex
    -0.46
    httphttps
    -0.45
    anthene
    -0.39
     pulled
    -0.38
    consulté
    -0.38
     consultato
    -0.37
     kasarigan
    -0.37
     thanks
    -0.37
    ädie
    -0.36
    ɵɵ
    -0.35
    POSITIVE LOGITS
     easier
    0.44
    Manbalar
    0.43
     avoid
    0.43
     cepat
    0.42
     easily
    0.42
     puissent
    0.42
    fromnode
    0.42
    Angebot
    0.41
     efficiently
    0.41
     accommodate
    0.40
    Activations Density 0.710%

    No Known Activations