© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11929
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to corporate and contractual obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    彼が
    -0.49
     él
    -0.43
    PrototypeOf
    -0.43
    彼は
    -0.42
    🇶
    -0.41
     yourself
    -0.41
    our
    -0.41
    ühr
    -0.40
    ifoli
    -0.40
    AddTagHelper
    -0.38
    POSITIVE LOGITS
     its
    2.02
    Its
    1.59
     Its
    1.52
     itself
    1.43
    它的
    1.37
     Оно
    1.28
    its
    1.21
     оно
    1.15
     Itself
    1.14
    itself
    1.12
    Activations Density 1.430%

    No Known Activations