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. 12717
    Prev
    Next
    INDEX
    Explanations

    information about new varieties of fruits, particularly concerning their characteristics and comparisons with existing varieties

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

    Word or phrase after "variety"

    np_acts-logits-general · gemini-2.0-flash

    plant and seed varieties

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    getWriter
    -0.51
    MemoryWarning
    -0.47
     doInBackground
    -0.46
     فريبيس
    -0.44
     BorderSide
    -0.42
    Біографія
    -0.40
     vest
    -0.36
     perio
    -0.35
    richment
    -0.35
     brinquedo
    -0.35
    POSITIVE LOGITS
     cultivars
    0.56
    Personendaten
    0.48
    estacks
    0.47
     genotype
    0.45
     cultivar
    0.44
     unggul
    0.44
     genotypes
    0.44
     strains
    0.44
     strain
    0.43
     qualités
    0.43
    Activations Density 0.527%

    No Known Activations