© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 4469
    Prev
    Next
    INDEX
    Explanations

    elements related to network ports and their corresponding numbers

    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
     Anſ
    -1.17
     pleaſure
    -1.16
     reaſon
    -1.09
     Monfieur
    -1.06
     raiſ
    -1.01
    lihood
    -1.00
     anſ
    -0.99
     Theſe
    -0.98
     Majefty
    -0.97
     uſed
    -0.96
    POSITIVE LOGITS
     Port
    1.82
     port
    1.67
     PORT
    1.62
    port
    1.60
    Port
    1.60
     Ports
    1.52
    PORT
    1.49
     ports
    1.44
    por
    1.41
    Ports
    1.35
    Activations Density 0.052%

    No Known Activations