© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 407
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal possession of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atalyst
    -0.81
    "}")
    -0.73
     Paglinawan
    -0.72
    Aiheesta
    -0.70
    =>
    -0.69
     mxArray
    -0.67
    Whitelist
    -0.66
    }))
    -0.66
    bildning
    -0.66
    ktm
    -0.66
    POSITIVE LOGITS
     possession
    1.40
     Possession
    1.31
     Poss
    1.26
    Poss
    1.26
     possessed
    1.20
    possession
    1.19
     possess
    1.13
     posses
    1.09
     possesses
    1.08
     blow
    1.05
    Activations Density 0.114%

    No Known Activations