© 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. 33-GEMMASCOPE-RES-16K
    11. 737
    Prev
    Next
    INDEX
    Explanations

    phrases related to penetration and infiltration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outgoing
    -0.43
    angered
    -0.38
    argout
    -0.38
    mycompany
    -0.38
    ziare
    -0.38
     plomo
    -0.38
    áctenos
    -0.38
    anair
    -0.37
     departing
    -0.36
    lijck
    -0.36
    POSITIVE LOGITS
     penetration
    1.49
     penetrate
    1.48
     penetrated
    1.42
     penet
    1.39
     penetrating
    1.35
     penetrates
    1.34
     Penetration
    1.34
     péné
    1.27
     проник
    1.26
    penet
    1.25
    Activations Density 0.577%

    No Known Activations