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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3353
    Prev
    Next
    INDEX
    Explanations

    terms related to kidney and lung conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    rungsseite
    -0.67
    ьаж
    -0.55
     समीक्षाएं
    -0.55
     ErrIntOverflow
    -0.53
    évaluateur
    -0.52
    ContentLoaded
    -0.50
    GenerationType
    -0.50
    portál
    -0.50
     lenker
    -0.49
    findpost
    -0.49
    POSITIVE LOGITS
    gdala
    0.43
    alamus
    0.41
     Nerven
    0.41
    MockMvc
    0.41
    brain
    0.39
     nerve
    0.39
    arynx
    0.38
    neum
    0.38
    Collider
    0.37
     Mitochond
    0.36
    Activations Density 0.932%

    No Known Activations