© 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. 7125
    Prev
    Next
    INDEX
    Explanations

    technical information and timestamps in a specific format within 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
    2019
    +0.26
    0.9%
    453
    +0.20
    0.7%
    1343
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.26
    0.04
    950
    +0.20
    0.04
    2019
    +0.13
    0.04
    Negative Logits
     unspeak
    -0.79
     motherfucker
    -0.75
     ineffec
    -0.71
     rascal
    -0.70
     multicolored
    -0.68
     horrend
    -0.67
     caucasian
    -0.66
     murmuring
    -0.66
     sophistic
    -0.65
     vainly
    -0.64
    POSITIVE LOGITS
     kafe
    0.75
     mikrofon
    0.74
     optik
    0.71
    //(
    0.69
     panik
    0.69
     keramik
    0.69
     protokol
    0.69
     elek
    0.68
     prostitu
    0.67
    #(
    0.67
    Activations Density 0.092%

    No Known Activations