Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 579
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or venues that offer unique experiences

    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
    1.1%
    1937
    +0.11
    0.7%
    1472
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1331
    +0.17
    0.04
    1472
    +0.11
    0.03
    1937
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.01
    ⓧ
    -0.76
    EndProject
    -0.68
    CreateIndex
    -0.68
    
    
    -0.67
     become
    -0.62
    Географи
    -0.61
    💼
    -0.59
     jsPsych
    -0.59
    /**
    -0.58
    POSITIVE LOGITS
     Bartholo
    1.50
     maneu
    1.46
     Minang
    1.38
     hcm
    1.36
     unwarran
    1.33
     disagre
    1.31
     Infir
    1.30
     Intere
    1.30
     Juf
    1.29
     ftre
    1.28
    Activations Density 0.166%

    No Known Activations