© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 99256
    Prev
    Next
    INDEX
    Explanations

    mentions of the ORCID identifier and associated links or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    IntoConstraints
    -0.53
    exitRule
    -0.50
    ReusableCell
    -0.49
    ViewInit
    -0.47
    makeConstraints
    -0.45
    GenerationType
    -0.44
    ConstraintMaker
    -0.43
    ConstraintLayout
    -0.42
     ujednoznacz
    -0.41
     linho
    -0.41
    POSITIVE LOGITS
    orcid
    1.02
    PasswordEncoder
    1.00
    isNameExpr
    0.84
     isNameExpr
    0.81
    abstractmethod
    0.77
    WEBPACK
    0.77
    BadRequest
    0.69
     aDecoder
    0.62
    chaikovsky
    0.55
    HasAnnotation
    0.54
    Activations Density 0.001%

    No Known Activations