© 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. 0-RES-JB
    11. 863
    Prev
    Next
    INDEX
    Explanations

    numerical or instructional steps that include a cautionary note

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1636
    +0.06
    0.2%
    1551
    +0.06
    0.2%
    50
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.06
    0.06
    491
    +0.06
    0.03
    1870
    +0.06
    -0.00
    Negative Logits
    ,
    -0.76
     remain
    -0.74
     serve
    -0.74
     des
    -0.74
    
    -0.73
     continue
    -0.72
    ੰ
    -0.71
     mit
    -0.71
     sit
    -0.71
    .
    -0.70
    POSITIVE LOGITS
     swarovski
    2.27
     maneu
    2.19
     emphat
    2.19
     affor
    2.17
     scrat
    2.16
     hairc
    2.15
     disagre
    2.14
     excru
    2.12
     perfet
    2.08
     increa
    2.07
    Activations Density 0.801%

    No Known Activations