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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4123
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession and legal implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.40
    Élet
    -0.37
     Privacidade
    -0.34
    şört
    -0.33
    гій
    -0.33
     României
    -0.33
     LIABLE
    -0.32
     PublicKey
    -0.30
    PyExc
    -0.30
    󠁴
    -0.30
    POSITIVE LOGITS
     possession
    2.72
    Poss
    2.52
     possessed
    2.48
     possess
    2.41
     Poss
    2.39
    poss
    2.34
     Possession
    2.34
    possession
    2.33
     posses
    2.30
     possesses
    2.23
    Activations Density 0.476%

    No Known Activations