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. 9075
    Prev
    Next
    INDEX
    Explanations

    information about prestigious, esteemed, or notable things or individuals

    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
    +0.19
    0.8%
    1385
    +0.14
    0.6%
    678
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.19
    0.16
    16
    +0.14
    0.11
    678
    +0.12
    0.13
    Negative Logits
    <bos>
    -3.04
    HasIndex
    -0.90
    /*
    
    -0.84
    |}
    -0.83
    styleType
    -0.82
    foreach
    -0.80
    addComponent
    -0.78
    /*
    -0.77
    //
    -0.77
    AddField
    -0.77
    POSITIVE LOGITS
     lyon
    2.08
     Juf
    2.01
     stockholm
    1.98
     sovere
    1.97
     aen
    1.92
     casio
    1.91
     wien
    1.91
     dises
    1.90
     napoli
    1.89
     Intere
    1.87
    Activations Density 1.693%

    No Known Activations