© 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. 16-GEMMASCOPE-RES-16K
    11. 10523
    Prev
    Next
    INDEX
    Explanations

    phrases related to declarations and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Help
    -0.44
    Mr
    -0.43
    Helps
    -0.43
    Autowired
    -0.43
    utils
    -0.42
     Bari
    -0.42
    ASSIST
    -0.42
    Funny
    -0.41
    στι
    -0.41
    Bari
    -0.41
    POSITIVE LOGITS
     declaration
    1.31
     declare
    1.23
     Declare
    1.22
     declarations
    1.18
     Declaration
    1.16
     declaring
    1.12
     declared
    1.08
     DECLARATION
    1.07
    Declare
    1.05
    declaration
    1.05
    Activations Density 0.117%

    No Known Activations