© 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. 6639
    Prev
    Next
    INDEX
    Explanations

    locations and countries

    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
    2034
    +0.13
    0.4%
    856
    +0.12
    0.3%
    939
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.13
    0.07
    939
    +0.12
    0.07
    102
    +0.11
    0.04
    Negative Logits
     maig
    -0.62
    Tja
    -0.61
    Witaj
    -0.60
     JULIO
    -0.59
    Cześć
    -0.54
    Komple
    -0.53
     notor
    -0.53
     elek
    -0.53
     Lombar
    -0.52
    Kleine
    -0.52
    POSITIVE LOGITS
     unwarran
    0.77
     whither
    0.74
     Wherever
    0.70
     wherea
    0.69
     Countries
    0.67
     fortn
    0.65
     increa
    0.65
     blest
    0.65
     accla
    0.65
     apprehen
    0.64
    Activations Density 0.888%

    No Known Activations