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. 15108
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or exclamation

    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
     myſelf
    -1.09
     himſelf
    -0.92
     themſelves
    -0.88
     houſe
    -0.88
     itſelf
    -0.86
     raiſ
    -0.83
    himself
    -0.79
     Houſe
    -0.76
     Efq
    -0.76
     perſon
    -0.74
    POSITIVE LOGITS
     Oh
    1.29
    Oh
    1.18
     oh
    1.10
    oh
    0.99
    Ohh
    0.98
     OH
    0.98
    Ohhh
    0.94
    Oooh
    0.90
    Ohhhh
    0.89
    toh
    0.85
    Activations Density 0.044%

    No Known Activations