© 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. 5825
    Prev
    Next
    INDEX
    Explanations

    numbers and specific quantifiers

    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
    +0.20
    0.9%
    568
    +0.11
    0.5%
    994
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    994
    +0.20
    0.06
    776
    +0.11
    0.12
    1526
    +0.11
    0.08
    Negative Logits
    <bos>
    -3.04
    ⓧ
    -0.94
    /***
    -0.88
    //});
    -0.84
    //{
    -0.78
    //};
    -0.74
    })();
    -0.70
     gynnwys
    -0.68
    Autoritní
    -0.67
    Демографія
    -0.66
    POSITIVE LOGITS
     ecru
    1.60
     tramont
    1.59
     napoli
    1.59
     milano
    1.56
     sappi
    1.54
     swarovski
    1.54
     valencia
    1.52
     bordeaux
    1.50
     viciss
    1.50
     bandung
    1.46
    Activations Density 2.182%

    No Known Activations