© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12580
    Prev
    Next
    INDEX
    Explanations

    places or territorial entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    812
    +0.13
    0.5%
    1127
    +0.13
    0.5%
    517
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.13
    0.02
    1056
    +0.13
    0.03
    981
    +0.12
    0.03
    Negative Logits
     osal
    -0.59
     mahd
    -0.52
    retmen
    -0.52
    wavering
    -0.51
     acoper
    -0.48
     sindaco
    -0.47
     Vienne
    -0.45
     Bourgogne
    -0.45
    ícil
    -0.45
    addPreferredGap
    -0.44
    POSITIVE LOGITS
     Lu
    1.18
     lu
    1.13
     LU
    1.11
     LUC
    1.11
    Lu
    1.10
     Luc
    0.98
    LU
    0.92
    LUC
    0.88
     Luk
    0.85
    lu
    0.85
    Activations Density 0.132%

    No Known Activations