© 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. 1740
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms related to billing, disclosure, and permissions

    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
    +0.15
    1.0%
    1492
    +0.13
    0.8%
    1472
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1492
    +0.15
    0.04
    553
    +0.13
    0.04
    241
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.70
    ⓧ
    -0.76
    
    -0.64
    Cyfarwyddwr
    -0.59
    <tfoot>
    -0.59
     onPostExecute
    -0.59
    <?
    -0.58
    /***
    -0.57
    <?
    -0.56
    delwed
    -0.54
    POSITIVE LOGITS
     Bill
    1.60
     bill
    1.56
    Bill
    1.53
     BILL
    1.37
    bill
    1.36
     bills
    1.34
     Bills
    1.33
    Bills
    1.30
    BILL
    1.29
    bills
    1.25
    Activations Density 0.106%

    No Known Activations