© 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. 6409
    Prev
    Next
    INDEX
    Explanations

    historical events and details related to acts of resistance

    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
    776
    +0.13
    0.4%
    559
    +0.12
    0.4%
    757
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    559
    +0.13
    0.04
    1512
    +0.12
    0.04
    517
    +0.12
    0.03
    Negative Logits
    chale
    -0.60
     ché
    -0.50
     estruct
    -0.47
    odore
    -0.47
     fú
    -0.47
    Reparto
    -0.45
     cuit
    -0.44
    hideLoading
    -0.44
     luy
    -0.43
    []=$
    -0.43
    POSITIVE LOGITS
     Later
    0.70
    Later
    0.66
     LATER
    0.64
     later
    0.63
    later
    0.58
     impractica
    0.55
     shewn
    0.53
     unwarran
    0.52
    quares
    0.52
     insuper
    0.51
    Activations Density 0.091%

    No Known Activations