© 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. 18-GEMMASCOPE-RES-16K
    11. 324
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to time and context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "in" or "from"

    np_acts-logits-general · gemini-2.0-flash

    prepositional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thither
    -0.76
     itſelf
    -0.69
     Majefty
    -0.63
     houſe
    -0.62
    Portale
    -0.62
     accordingly
    -0.62
    fromnode
    -0.61
     Asimismo
    -0.61
    PrototypeOf
    -0.61
    RenderAtEndOf
    -0.61
    POSITIVE LOGITS
     my
    0.73
    MLLoader
    0.60
    AccessorTable
    0.56
     past
    0.52
     tengo
    0.51
     تضيفلها
    0.51
     meine
    0.51
     googling
    0.49
     what
    0.49
    Personendaten
    0.49
    Activations Density 0.245%

    No Known Activations