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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 5914
    Prev
    Next
    INDEX
    Explanations

    names of geographical locations and associated entities

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

    geographical locations and place names, particularly U.S. states and cities.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⤹
    -0.63
     Roskov
    -0.56
     оригіналу
    -0.54
    +#+#
    -0.52
    IndentedString
    -0.52
    TargetException
    -0.51
    ervlak
    -0.51
    โย
    -0.50
     esternos
    -0.50
     utafitiHapana
    -0.50
    POSITIVE LOGITS
     Seattle
    1.27
     Spokane
    1.14
    Seattle
    1.13
     Puget
    1.11
     Tacoma
    1.07
     Yakima
    1.03
     Vancouver
    0.98
     Oregon
    0.89
     Bellingham
    0.88
    seattle
    0.83
    Activations Density 0.231%

    No Known Activations