© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3488
    Prev
    Next
    INDEX
    Explanations

    LED lighting details and technical specifications

    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
    1271
    +0.15
    0.8%
    50
    +0.13
    0.7%
    1392
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1271
    +0.15
    0.04
    1974
    +0.13
    0.03
    1921
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.11
    omaterial
    -0.57
    matchCondition
    -0.55
    ppins
    -0.53
    /*++
    -0.52
    lıyor
    -0.52
    <?
    -0.50
    ždý
    -0.50
     viewWillAppear
    -0.50
    WarningLevel
    -0.49
    POSITIVE LOGITS
     Led
    1.23
    Led
    1.22
     LED
    1.05
    LED
    1.02
     LEDs
    0.94
     led
    0.93
    led
    0.93
     leds
    0.90
     Middles
    0.86
     élev
    0.84
    Activations Density 0.260%

    No Known Activations