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. 8-GEMMASCOPE-RES-16K
    6. 5651
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to land and its usage or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Valerio
    -0.85
     Erfurt
    -0.83
    tems
    -0.83
    onNext
    -0.82
     Hogg
    -0.80
    >>>>>
    -0.77
     simplex
    -0.77
     Parigi
    -0.76
     Polri
    -0.76
     neceff
    -0.76
    POSITIVE LOGITS
     LAND
    1.72
     Land
    1.64
     land
    1.54
    Land
    1.48
    land
    1.42
     Lands
    1.37
     Landis
    1.36
     Landry
    1.35
     lands
    1.32
    lands
    1.31
    Activations Density 0.041%

    No Known Activations