© 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. 12300
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    +0.22
    0.6%
    1533
    +0.07
    0.2%
    1560
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.22
    0.00
    0
    -0.07
    0.00
    1
    -0.06
    0.00
    Negative Logits
     impra
    -2.98
     reluct
    -2.96
     increa
    -2.91
     disagre
    -2.85
     unwarran
    -2.78
     inev
    -2.75
     unspeak
    -2.74
     unlaw
    -2.74
     unden
    -2.72
     affor
    -2.70
    POSITIVE LOGITS
    <bos>
    5.46
    newswire
    1.38
    expandindo
    1.20
    SourceChecksum
    1.03
     betweenstory
    1.02
    IsMutable
    0.98
    GEBURTSDATUM
    0.98
     Италијани
    0.93
    脚注の使い方
    0.93
     Wiktionnaire
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.