© 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. 1845
    Prev
    Next
    INDEX
    Explanations

    numerical figures and statistics

    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
    998
    +0.12
    0.4%
    1224
    +0.11
    0.4%
    1177
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1417
    +0.12
    0.03
    956
    +0.11
    0.02
    1978
    +0.10
    0.05
    Negative Logits
    IsContent
    -0.94
     Walkover
    -0.79
    ValueStyle
    -0.77
    RegistryLite
    -0.76
    BeginInit
    -0.71
    xodo
    -0.70
    ]=>
    -0.69
    delwed
    -0.69
    ніципалі
    -0.68
    tagHelperRunner
    -0.68
    POSITIVE LOGITS
     depic
    2.18
     disagre
    2.18
     impra
    2.15
     suscep
    2.10
     unve
    2.10
     inev
    2.07
     reluct
    2.06
     encomp
    2.05
     affor
    2.04
     maneu
    2.03
    Activations Density 0.676%

    No Known Activations