© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 8305
    Prev
    Next
    INDEX
    Explanations

    certain types of information such as copyright notices, release dates, and clinical trial details

    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
    50
    +0.14
    0.4%
    994
    +0.10
    0.3%
    1691
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1213
    +0.14
    0.05
    1210
    +0.10
    0.04
    91
    +0.09
    0.04
    Negative Logits
     intersper
    -1.71
     quitted
    -1.51
     snoopy
    -1.48
     reluct
    -1.44
     affor
    -1.43
     encomp
    -1.42
     strick
    -1.40
     apprehen
    -1.39
     tolerably
    -1.38
     gild
    -1.36
    POSITIVE LOGITS
    Copyright
    0.77
    setMaximum
    0.72
    setEditable
    0.70
     Copyright
    0.70
    copyright
    0.69
     Ciò
    0.68
     Queste
    0.63
    setVertical
    0.63
     Tuttavia
    0.62
    setMinimumSize
    0.61
    Activations Density 0.061%

    No Known Activations