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

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 9501
    Prev
    Next
    INDEX
    Explanations

    phrases related to methods and techniques used in scientific research and analysis

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

    a process or method

    np_acts-logits-general · gemini-2.0-flash

    methods and techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.42
    
    -0.39
    ленность
    -0.38
    NameValuePair
    -0.37
    ItemBackground
    -0.34
    NameInMap
    -0.34
    mogat
    -0.32
     AssemblyCulture
    -0.32
    parsedMessage
    -0.32
    OutOfRange
    -0.32
    POSITIVE LOGITS
     method
    2.55
     methods
    2.38
    method
    2.25
     Method
    2.20
     método
    2.19
     méthode
    2.19
    Method
    2.09
     technique
    2.06
     metod
    2.05
    methods
    2.03
    Activations Density 1.694%

    No Known Activations