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. 2353
    Prev
    Next
    INDEX
    Explanations

    design-related terms and computer-related activities

    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
    1343
    +0.12
    0.5%
    50
    +0.12
    0.5%
    1150
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.12
    0.19
    2044
    +0.12
    0.15
    227
    +0.11
    0.13
    Negative Logits
    <bos>
    -2.21
     endwhile
    -0.73
    protected
    -0.69
     springfox
    -0.66
     onResponse
    -0.66
    circ
    -0.63
    ItemBackground
    -0.63
    WithMany
    -0.62
    ുറ
    -0.62
    apnews
    -0.62
    POSITIVE LOGITS
     affor
    2.33
     maneu
    2.30
     accla
    2.19
     shenan
    2.15
     increa
    2.13
     impra
    2.12
     disagre
    2.09
     reluct
    2.00
     guarante
    1.99
     strick
    1.97
    Activations Density 0.772%

    No Known Activations