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. 8169
    Prev
    Next
    INDEX
    Explanations

    information related to educational systems and standards

    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
    1222
    +0.15
    0.9%
    1096
    +0.15
    0.8%
    2004
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.05
    1634
    +0.15
    0.04
    1741
    +0.14
    -0.00
    Negative Logits
    <bos>
    -1.43
    mergeFrom
    -0.83
     BoxFit
    -0.81
    UnusedPrivate
    -0.66
    Varint
    -0.64
    <?
    -0.61
    AddTagHelper
    -0.61
     '{@
    -0.60
    iprot
    -0.59
    гән
    -0.59
    POSITIVE LOGITS
     affor
    1.49
     aen
    1.36
     vne
    1.32
     disreg
    1.31
     unce
    1.29
     guarante
    1.29
     maneu
    1.28
     mcc
    1.26
     hairc
    1.26
     secon
    1.24
    Activations Density 0.546%

    No Known Activations