© 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. 12765
    Prev
    Next
    INDEX
    Explanations

    mentions of censorship or restrictions

    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
    381
    +0.13
    0.4%
    1535
    +0.12
    0.4%
    1705
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.13
    0.04
    994
    +0.12
    0.03
    484
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.18
    Fakta
    -0.72
    Glej
    -0.72
     philanth
    -0.71
     unspeak
    -0.68
    bouncycastle
    -0.67
    calciatore
    -0.66
    Ekster
    -0.66
     adjour
    -0.65
     Reprinted
    -0.65
    POSITIVE LOGITS
     cyr
    1.15
     ananas
    1.12
    quarelle
    1.06
     abnorm
    1.01
     sord
    1.00
     jawa
    0.98
     albic
    0.89
     maroc
    0.88
     babi
    0.87
    uberge
    0.87
    Activations Density 0.149%

    No Known Activations