© 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. 14731
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing a particular viewpoint or argument

    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
    872
    +0.10
    0.3%
    1719
    +0.08
    0.2%
    470
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    454
    +0.10
    0.02
    1355
    +0.08
    0.03
    872
    +0.07
    0.04
    Negative Logits
    capulco
    -0.82
     kani
    -0.81
     susun
    -0.78
     magis
    -0.77
     ibiza
    -0.76
     guma
    -0.75
     haup
    -0.74
    tionally
    -0.73
    dirond
    -0.72
     canel
    -0.71
    POSITIVE LOGITS
     point
    1.00
    point
    0.86
     Point
    0.79
     POINT
    0.77
    Point
    0.74
    POINT
    0.73
     points
    0.67
     punto
    0.64
    points
    0.61
     argument
    0.60
    Activations Density 0.218%

    No Known Activations