© 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. 23-GEMMASCOPE-RES-16K
    11. 8821
    Prev
    Next
    INDEX
    Explanations

    references to characters involved in covert operations or undercover roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ælp
    -0.56
     craindre
    -0.55
     prouver
    -0.54
     défendre
    -0.53
    SizeF
    -0.50
     préciser
    -0.50
    RegisterType
    -0.50
     giornal
    -0.49
     mourir
    -0.49
     résoudre
    -0.48
    POSITIVE LOGITS
     person
    1.78
     researcher
    1.50
     musician
    1.48
     worker
    1.45
     guy
    1.45
     participant
    1.44
     performer
    1.43
     player
    1.43
     member
    1.41
     scientist
    1.38
    Activations Density 3.109%

    No Known Activations