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. 14120
    Prev
    Next
    INDEX
    Explanations

    references to authors or professionals recommending or endorsing other works or services

    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
    +0.18
    0.7%
    1614
    +0.10
    0.4%
    1987
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1987
    +0.18
    0.11
    1614
    +0.10
    0.08
    1013
    +0.10
    0.11
    Negative Logits
    <bos>
    -1.25
    ⓧ
    -0.85
    
    
    -0.73
    DataPropertyName
    -0.73
     ser
    -0.70
     som
    -0.68
     الحره
    -0.67
     she
    -0.67
     qui
    -0.67
    fvar
    -0.66
    POSITIVE LOGITS
     maneu
    1.96
     sergio
    1.96
     inev
    1.95
     roberto
    1.87
     increa
    1.87
     ricardo
    1.86
     jorge
    1.84
     alberto
    1.84
     leonardo
    1.82
     bayern
    1.81
    Activations Density 1.509%

    No Known Activations