© 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. 6515
    Prev
    Next
    INDEX
    Explanations

    details about software updates, improvements, and bug fixes

    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
    1842
    +0.36
    1.4%
    184
    +0.33
    1.2%
    1577
    +0.22
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.36
    0.05
    1842
    +0.33
    0.07
    1343
    +0.22
    0.06
    Negative Logits
     impra
    -1.09
     uninten
    -1.07
     unden
    -1.04
     indestru
    -1.03
     encomp
    -1.00
     reluct
    -0.99
     affor
    -0.98
     philanth
    -0.98
     volunte
    -0.98
     unwarran
    -0.97
    POSITIVE LOGITS
    TagMode
    0.62
     للمعارف
    0.55
    BoxShadow
    0.53
    XmlIgnore
    0.53
    rrggbb
    0.50
    IsContent
    0.49
    ExecuteReader
    0.47
    gdala
    0.46
     становника
    0.46
    ServletException
    0.45
    Activations Density 0.565%

    No Known Activations