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. 15-GEMMASCOPE-RES-16K
    6. 2880
    Prev
    Next
    INDEX
    Explanations

    dates and references related to specific time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.99
    OGND
    -0.96
    stdc
    -0.90
    WithIOException
    -0.87
    Personendaten
    -0.86
    Geplaatst
    -0.86
    RenderAtEndOf
    -0.82
    enterOuterAlt
    -0.81
    rostis
    -0.80
    "):
    
    -0.80
    POSITIVE LOGITS
    日閲覧
    0.52
    .
    0.48
    。
    0.45
     numériques
    0.43
     dû
    0.41
     occupé
    0.41
     partenza
    0.41
     sanitaires
    0.41
     piş
    0.40
     fuite
    0.40
    Activations Density 0.031%

    No Known Activations