© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1773
    Prev
    Next
    INDEX
    Explanations

    topics related to ongoing processes or projects

    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
    1757
    +0.18
    0.9%
    478
    +0.13
    0.7%
    1101
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1757
    +0.18
    0.04
    156
    +0.13
    0.03
    1101
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.84
    InjectMocks
    -0.81
    ⓧ
    -0.69
     onView
    -0.64
    Ос
    -0.63
    DataPropertyName
    -0.63
    República
    -0.63
    <?
    -0.63
    <?
    -0.63
    prop
    -0.62
    POSITIVE LOGITS
     fta
    1.75
     casio
    1.71
     fte
    1.69
     stockholm
    1.68
     aen
    1.65
     sml
    1.64
     afo
    1.60
     ftu
    1.57
     fup
    1.57
     lyon
    1.57
    Activations Density 0.404%

    No Known Activations