© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7598
    Prev
    Next
    INDEX
    Explanations

    various techniques and methods related to technology and processes

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

    "technique" or "techniques"

    np_acts-logits-general · gemini-2.0-flash

    techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.79
    󠁮
    -0.72
     queſta
    -0.56
    AndEndTag
    -0.54
    friger
    -0.50
    StoreMessageInfo
    -0.49
    دانشنامهٔ
    -0.49
    뀔
    -0.48
    ConstraintMaker
    -0.46
    bited
    -0.46
    POSITIVE LOGITS
     techniques
    1.95
     technique
    1.84
     Techniques
    1.77
    Techniques
    1.74
    techniques
    1.72
     Technique
    1.68
    Technique
    1.63
     TECHNIQUES
    1.62
    technique
    1.59
     TECHNIQUE
    1.54
    Activations Density 0.211%

    No Known Activations