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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 8498
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to flipping or changing in various contexts

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

    "flip" and its variations

    np_acts-logits-general · gemini-2.0-flash

    flip and flip 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
    存于互联网档案馆
    -0.66
    Bakgrunnsstoff
    -0.61
    సు
    -0.57
     typelib
    -0.57
    initializeApp
    -0.56
    Abp
    -0.56
    okhttp
    -0.54
     rekening
    -0.54
    ngrx
    -0.52
     חיצוניים
    -0.52
    POSITIVE LOGITS
     flip
    1.31
     flips
    1.29
     flipping
    1.22
     Flip
    1.19
     flipped
    1.18
    flip
    1.12
    Flip
    1.11
     Fli
    1.04
     coin
    1.03
    FLIP
    1.00
    Activations Density 0.108%

    No Known Activations