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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 6073
    Prev
    Next
    INDEX
    Explanations

    references to ports and related structures in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    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
    -1.19
     pleaſure
    -1.18
     reaſon
    -1.14
     Monfieur
    -1.14
     raiſ
    -1.04
     anſ
    -1.03
    lihood
    -1.02
     Theſe
    -1.02
     ſame
    -1.02
     Efq
    -1.01
    POSITIVE LOGITS
     Port
    1.53
     PORT
    1.43
     Ports
    1.37
    por
    1.36
    Port
    1.33
    port
    1.32
     POR
    1.30
     port
    1.30
    PORT
    1.28
    Ports
    1.21
    Activations Density 0.080%

    No Known Activations