© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6667
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to transportation and engineering

    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
    674
    +0.10
    0.3%
    327
    +0.07
    0.2%
    1868
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1295
    +0.10
    0.02
    181
    +0.07
    0.02
    536
    +0.06
    0.02
    Negative Logits
     unspeak
    -1.30
     Daven
    -1.27
     impelled
    -1.26
     McLaugh
    -1.18
     unve
    -1.18
     tolerably
    -1.14
     vainly
    -1.13
     sculptured
    -1.13
     gaily
    -1.09
     withal
    -1.09
    POSITIVE LOGITS
     manuten
    1.15
     marte
    1.15
     poliuret
    0.99
     fono
    0.96
     frambo
    0.95
    <bos>
    0.93
     guir
    0.92
     tenda
    0.92
     veu
    0.91
     maniere
    0.90
    Activations Density 0.048%

    No Known Activations