© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 1249
    Prev
    Next
    INDEX
    Explanations

    email signatures or contact information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1141
    +0.15
    0.8%
    1339
    +0.15
    0.7%
    11
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.15
    0.03
    1097
    +0.15
    0.05
    1741
    +0.14
    -0.00
    Negative Logits
     encomp
    -1.13
     intersper
    -1.12
     friable
    -1.08
     stratigraph
    -1.01
     impractica
    -0.99
     Daven
    -0.96
     unve
    -0.95
     jorge
    -0.94
     tawny
    -0.94
     Marín
    -0.94
    POSITIVE LOGITS
    ________________
    1.18
    ................
    0.75
    ----------------
    0.69
     ________
    0.67
    _______________
    0.67
    RectangleBorder
    0.66
    (_
    0.66
    ______
    0.65
    ________
    0.63
    %%%%%%%%%%%%%%%%
    0.63
    Activations Density 0.552%

    No Known Activations