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

    Neuronpedia

    Jacobian LensNEW
    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. 1793
    Prev
    Next
    INDEX
    Explanations

    statements related to personal beliefs, values, and activism

    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
    +0.15
    0.7%
    2015
    +0.10
    0.5%
    478
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2015
    +0.15
    -0.01
    184
    +0.10
    -0.04
    764
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.95
     intersper
    -1.37
     inaugurate
    -1.09
     endow
    -1.07
    /***
    -1.01
     inconce
    -1.01
     benevol
    -0.98
     rouse
    -0.97
     shenan
    -0.96
    <?
    -0.96
    POSITIVE LOGITS
     bicic
    0.85
     moza
    0.72
     marea
    0.71
     birra
    0.71
     tricot
    0.70
     benzin
    0.69
     lampada
    0.67
    *</
    0.66
     borsa
    0.66
    SneakyThrows
    0.65
    Activations Density 2.348%

    No Known Activations