© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14675
    Prev
    Next
    INDEX
    Explanations

    numerical data and figures

    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
    1343
    +0.16
    0.5%
    137
    +0.14
    0.5%
    227
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.16
    0.09
    1009
    +0.14
    0.04
    184
    +0.12
    0.02
    Negative Logits
    StoreMessageInfo
    -0.81
     gynhyrchwyd
    -0.79
     Administrativna
    -0.74
    <bos>
    -0.73
     հղումներ
    -0.72
    SourceChecksum
    -0.71
     otomatig
    -0.69
     AssemblyCulture
    -0.68
     Italijani
    -0.67
    richTextPanel
    -0.65
    POSITIVE LOGITS
     vns
    1.36
     fta
    1.34
     »>
    1.33
     ftu
    1.32
     fign
    1.32
     fep
    1.32
     squa
    1.29
     fath
    1.29
     fuf
    1.28
     increa
    1.28
    Activations Density 0.666%

    No Known Activations