© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6962
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific step or method in a detailed process or procedure

    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
    +0.20
    1.3%
    1870
    +0.11
    0.7%
    966
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    966
    +0.20
    0.04
    1708
    +0.11
    0.03
    789
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.54
    ⓧ
    -0.94
    /***
    -0.76
    <?
    -0.69
     mobilize
    -0.67
    /*++
    -0.65
    /**
    -0.65
     admit
    -0.64
    public
    -0.64
     expand
    -0.63
    POSITIVE LOGITS
     lele
    1.60
     jaya
    1.59
     Minang
    1.56
     bandung
    1.55
     kasa
    1.47
     jawa
    1.45
     milano
    1.44
     Juf
    1.43
     affor
    1.41
     bangkok
    1.40
    Activations Density 0.107%

    No Known Activations