© 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. 13346
    Prev
    Next
    INDEX
    Explanations

    images mentioned in the text

    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
    906
    +0.13
    0.4%
    872
    +0.09
    0.3%
    1856
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1856
    +0.13
    0.07
    1018
    +0.09
    0.03
    678
    +0.09
    0.05
    Negative Logits
     Joaqu
    -0.84
     jorge
    -0.80
     Asunción
    -0.80
     Valentín
    -0.80
     silikon
    -0.79
     kompati
    -0.79
     ricardo
    -0.79
     Áng
    -0.78
     Meksi
    -0.77
     alkoh
    -0.77
    POSITIVE LOGITS
     image
    0.83
     images
    0.77
    image
    0.74
     img
    0.67
     Image
    0.65
    Image
    0.63
     imagen
    0.60
    images
    0.60
     photograph
    0.59
     photo
    0.59
    Activations Density 0.594%

    No Known Activations