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. 8-GEMMASCOPE-RES-16K
    6. 11335
    Prev
    Next
    INDEX
    Explanations

    the beginning of text segments, indicating the start of new content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.59
    uktur
    -0.53
     and
    -0.53
     but
    -0.50
     MusicBrainz
    -0.48
    Amicalement
    -0.48
    Externé
    -0.47
     Отечественной
    -0.46
    IMDG
    -0.46
    HasMaxLength
    -0.45
    POSITIVE LOGITS
     ſtate
    0.79
     Majefty
    0.78
     Chriftian
    0.76
     AppColors
    0.76
     ſch
    0.75
     Jefus
    0.75
     Chriſt
    0.75
    MENAFN
    0.75
     Reſ
    0.74
    __":
    
    0.73
    Activations Density 0.084%

    No Known Activations