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. 7-GEMMASCOPE-RES-16K
    6. 14502
    Prev
    Next
    INDEX
    Explanations

    terms related to atmospheric properties and planetary characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breech
    -0.47
     dilution
    -0.46
    ikations
    -0.46
    Orsay
    -0.46
    lucent
    -0.45
     genio
    -0.44
    haru
    -0.44
    (")");
    -0.44
     spurious
    -0.44
    ragona
    -0.44
    POSITIVE LOGITS
     MotionEvent
    0.76
    istoitu
    0.73
     planet
    0.73
     &___
    0.71
     MainAxisSize
    0.64
    Atsauces
    0.63
    Portály
    0.63
     оригіналу
    0.62
    الإنجليزية
    0.62
     planets
    0.62
    Activations Density 0.234%

    No Known Activations