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. 14795
    Prev
    Next
    INDEX
    Explanations

    legal terms and restrictions

    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
    +0.18
    0.7%
    438
    +0.16
    0.7%
    2036
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.18
    0.09
    1784
    +0.16
    0.07
    581
    +0.10
    0.06
    Negative Logits
    <bos>
    -2.63
     and
    -0.66
     also
    -0.63
    ,
    -0.61
     instead
    -0.59
     SwitchCompat
    -0.58
    //---
    -0.57
     ve
    -0.56
    ///**
    -0.56
    .
    -0.56
    POSITIVE LOGITS
     thut
    1.64
     ftu
    1.63
     fta
    1.63
     dises
    1.57
     aen
    1.52
     milano
    1.52
     perfon
    1.51
     roberto
    1.51
     tramont
    1.51
     sergio
    1.50
    Activations Density 1.027%

    No Known Activations