© 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. 4008
    Prev
    Next
    INDEX
    Explanations

    scientific and technical information related to space exploration and research

    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
    1499
    +0.09
    0.2%
    1415
    +0.08
    0.2%
    1097
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.09
    0.04
    1780
    +0.08
    0.03
    1499
    +0.07
    0.05
    Negative Logits
     philanth
    -1.31
     affor
    -1.29
     michelin
    -1.29
     Juf
    -1.25
     pamph
    -1.24
     pican
    -1.23
     Souha
    -1.23
     shenan
    -1.22
     unspeak
    -1.22
     Haci
    -1.21
    POSITIVE LOGITS
     determine
    0.77
     heapq
    0.72
    SourceChecksum
    0.70
    <bos>
    0.69
     smtplib
    0.68
     insights
    0.67
    confirm
    0.66
     pylab
    0.65
    AndEndTag
    0.65
     confirm
    0.65
    Activations Density 0.346%

    No Known Activations