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. 5311
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    +0.14
    0.8%
    645
    +0.12
    0.7%
    893
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    645
    +0.14
    0.05
    332
    +0.12
    0.04
    1267
    +0.09
    0.03
    Negative Logits
    <bos>
    -3.16
    ⓧ
    -1.01
    /**
    -0.87
    
    
    -0.83
    EndProject
    -0.80
    /*
    -0.79
    BASELINE
    -0.77
    glLoadIdentity
    -0.75
     prepare
    -0.73
    glBind
    -0.72
    POSITIVE LOGITS
     maneu
    2.15
     Juf
    2.12
     mef
    2.12
     stockholm
    2.10
     Augu
    2.04
     wien
    2.03
     eiffel
    2.02
     fta
    2.00
     hcm
    2.00
     aen
    1.99
    Activations Density 0.032%

    No Known Activations