© 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. 6752
    Prev
    Next
    INDEX
    Explanations

    historical and biographical information, potentially focusing on acts of heroism and notable individuals

    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
    184
    +0.36
    1.4%
    764
    +0.31
    1.2%
    1967
    +0.20
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.36
    0.01
    764
    +0.31
    0.01
    1009
    +0.20
    0.01
    Negative Logits
     impra
    -1.16
     uninten
    -1.07
     maneu
    -1.00
     invin
    -0.98
     shenan
    -0.93
     inconce
    -0.92
     vagu
    -0.91
     vété
    -0.89
     perfet
    -0.89
     excru
    -0.89
    POSITIVE LOGITS
    <bos>
    0.66
    Espèce
    0.60
    shadowRadius
    0.58
    principalColumn
    0.56
    IsContent
    0.56
     otomatig
    0.56
    ibouti
    0.53
     Himo
    0.53
     typelib
    0.52
     SIMBAD
    0.51
    Activations Density 0.014%

    No Known Activations