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. 5441
    Prev
    Next
    INDEX
    Explanations

    references related to technology specifications, gaming equipment, and organizations or groups

    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
    1335
    +0.15
    0.8%
    90
    +0.15
    0.8%
    1328
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.05
    1328
    +0.15
    0.05
    1741
    +0.14
    -0.00
    Negative Logits
    <bos>
    -0.81
     vectorial
    -0.71
     Ceux
    -0.69
     Ename
    -0.69
    deutung
    -0.69
     Transverse
    -0.68
     convenable
    -0.67
     unlaw
    -0.65
     Poincar
    -0.65
    expandindo
    -0.64
    POSITIVE LOGITS
     Delta
    0.86
    Delta
    0.79
     minimalis
    0.71
     Δ
    0.68
     triangle
    0.68
     habang
    0.67
     delta
    0.66
     maksimum
    0.65
     pyramid
    0.65
     kram
    0.65
    Activations Density 0.625%

    No Known Activations