© 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. 6583
    Prev
    Next
    INDEX
    Explanations

    phrases related to philosophical and social commentary discussing controversial topics

    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
    394
    +0.10
    0.3%
    468
    +0.08
    0.2%
    1533
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.10
    0.05
    1705
    +0.08
    0.06
    2026
    +0.08
    0.04
    Negative Logits
    umacher
    -0.58
     dizaine
    -0.53
     дописавши
    -0.53
    SourceChecksum
    -0.52
    MathML
    -0.52
     Resmi
    -0.52
     itinéraire
    -0.51
     panneau
    -0.50
     courriel
    -0.49
    nitzer
    -0.49
    POSITIVE LOGITS
     tricot
    0.88
     canel
    0.82
     pican
    0.80
     divertimento
    0.78
     bordeaux
    0.78
     swarovski
    0.74
     eccell
    0.72
     ecru
    0.72
     tupperware
    0.72
     funghi
    0.70
    Activations Density 0.418%

    No Known Activations