Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7817
    Prev
    Next
    INDEX
    Explanations

    items related to food, dining, and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pungkasnya
    -0.46
    __':
    
    -0.44
    rifuge
    -0.41
    hyrchwyd
    -0.40
    </blockquote>
    -0.40
     OMITBAD
    -0.39
    쩌
    -0.38
     betweenstory
    -0.38
    seamnă
    -0.38
    ."""
    -0.37
    POSITIVE LOGITS
     HasFactory
    0.61
     تضيفلها
    0.54
     ModelExpression
    0.53
    aktur
    0.48
     كومونز
    0.48
     utafitiHapana
    0.47
     Мексичка
    0.44
    KURZBESCHREIBUNG
    0.43
    AnchorStyles
    0.43
    Personendaten
    0.43
    Activations Density 0.417%

    No Known Activations