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. 2-GEMMASCOPE-RES-16K
    6. 2179
    Prev
    Next
    INDEX
    Explanations

    terms related to navigation systems and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -1.27
    uxxxx
    -0.87
    ValueStyle
    -0.86
    tvguidetime
    -0.80
    contentLoaded
    -0.76
    HideFlags
    -0.73
    Hentet
    -0.67
    ftagPool
    -0.66
    Билгалдахарш
    -0.65
     nahilalakip
    -0.63
    POSITIVE LOGITS
     navigation
    3.29
     Navigation
    3.13
    Navigation
    2.94
    navigation
    2.80
     Navig
    2.53
     navig
    2.53
    Navig
    2.41
     NAVIGATION
    2.37
     navigate
    2.31
    navig
    2.23
    Activations Density 0.016%

    No Known Activations