© 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. 1791
    Prev
    Next
    INDEX
    Explanations

    comparisons and evaluations in the text

    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
    +0.17
    0.9%
    1828
    +0.15
    0.8%
    1407
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.17
    0.06
    1828
    +0.15
    0.06
    755
    +0.13
    0.05
    Negative Logits
    <bos>
    -3.56
    /***
    -0.80
    HasColumnType
    -0.73
    get
    -0.73
    contentLoaded
    -0.72
    public
    -0.71
     John
    -0.71
    styleType
    -0.70
    Comun
    -0.70
    cdk
    -0.69
    POSITIVE LOGITS
     maneu
    2.18
     affor
    2.16
     ecru
    2.13
     increa
    2.05
     impra
    2.04
     milano
    2.04
     stockholm
    2.01
     accla
    2.00
     napoli
    2.00
     wikihow
    1.99
    Activations Density 0.099%

    No Known Activations