Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2197
    Prev
    Next
    INDEX
    Explanations

    phrases related to preparation and readiness for action

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

    preparation or readiness

    np_acts-logits-general · gemini-2.0-flash

    getting ready for events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    つい
    -0.42
    mittent
    -0.40
    aneta
    -0.40
     Weller
    -0.40
     konusu
    -0.39
     SDLK
    -0.38
     cayó
    -0.38
    lodash
    -0.37
    lain
    -0.37
    InOut
    -0.37
    POSITIVE LOGITS
     preparation
    2.96
     prepare
    2.69
     prepared
    2.69
     Preparation
    2.69
     ready
    2.66
    preparation
    2.63
     readiness
    2.56
     preparations
    2.52
     prepares
    2.51
     preparing
    2.48
    Activations Density 0.299%

    No Known Activations