© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11533
    Prev
    Next
    INDEX
    Explanations

    unsure or speculative statements made by 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
    674
    +0.11
    0.3%
    671
    +0.09
    0.3%
    1510
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    671
    +0.11
    0.03
    1625
    +0.09
    0.03
    1101
    +0.09
    0.03
    Negative Logits
     unspeak
    -0.83
     inconce
    -0.82
     indestru
    -0.79
     emphat
    -0.77
     reluct
    -0.77
     philanth
    -0.75
     intrigu
    -0.74
     ineffec
    -0.74
     indescri
    -0.74
     unwarran
    -0.72
    POSITIVE LOGITS
    <bos>
    0.95
    GEBURTSDATUM
    0.64
     سكانية
    0.61
     Normdatei
    0.60
    HostException
    0.59
     kaynağından
    0.56
     مرئيه
    0.56
     ISNI
    0.56
     gawas
    0.55
    MessageOf
    0.54
    Activations Density 0.162%

    No Known Activations