© 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. 792
    Prev
    Next
    INDEX
    Explanations

    descriptions related to events, possibly related to a news story or press coverage

    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
    1577
    +0.40
    1.6%
    599
    +0.22
    0.9%
    394
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.40
    0.27
    184
    +0.22
    0.06
    1129
    +0.15
    0.21
    Negative Logits
     simplif
    -0.97
     lidl
    -0.94
     sappi
    -0.93
     milf
    -0.92
     Juf
    -0.91
     !...
    -0.91
     ?...
    -0.91
     peppa
    -0.91
     Messieurs
    -0.90
     bangkok
    -0.89
    POSITIVE LOGITS
    </i>
    0.78
    </em>
    0.71
    .”
    0.66
    ,”
    0.65
     [
    0.65
    !”
    0.63
    </b>
    0.61
    ."
    0.60
    ,"
    0.60
    ”
    0.58
    Activations Density 8.287%

    No Known Activations