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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7287
    Prev
    Next
    INDEX
    Explanations

    references to "port" and its different contexts, including geographical and technical uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "port" and its variations

    np_acts-logits-general · gemini-2.0-flash

    port followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.82
    NUMX
    -0.77
    HasAnnotation
    -0.76
    AndroidJUnit
    -0.75
     Réponses
    -0.75
    __':
    -0.74
     calendriers
    -0.73
     beginnetje
    -0.72
    apimachinery
    -0.71
    ⤹
    -0.69
    POSITIVE LOGITS
     PORT
    0.59
     Por
    0.58
     POR
    0.57
     Port
    0.56
     Ports
    0.56
    folium
    0.55
     lot
    0.55
     por
    0.54
    rayed
    0.54
    por
    0.53
    Activations Density 0.090%

    No Known Activations