© 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. 8575
    Prev
    Next
    INDEX
    Explanations

    mentions of specific software or hardware products

    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
    1334
    +0.16
    0.8%
    1921
    +0.13
    0.7%
    1964
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.16
    0.00
    1363
    +0.13
    0.03
    1334
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.18
    Tikang
    -0.59
     shuddered
    -0.53
     Kalimantan
    -0.52
     corral
    -0.52
     reel
    -0.51
     enshr
    -0.51
     expel
    -0.50
     ensue
    -0.50
    reel
    -0.49
    POSITIVE LOGITS
     MB
    1.27
    MB
    1.19
    mb
    0.91
     mb
    0.90
     Mb
    0.88
    Mb
    0.81
     Benz
    0.76
     tremb
    0.75
     teneb
    0.75
    Benz
    0.73
    Activations Density 0.480%

    No Known Activations