© 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. 1589
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Is" followed by a statement or a situation

    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
    +0.27
    1.8%
    1937
    +0.19
    1.3%
    2011
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.27
    0.20
    2011
    +0.19
    0.10
    662
    +0.12
    0.11
    Negative Logits
    <bos>
    -3.96
    ⓧ
    -0.71
    
    -0.67
    Kontrola
    -0.67
    <?
    -0.67
    Autoritní
    -0.65
    //---
    -0.64
    migrationBuilder
    -0.63
    Vegeu
    -0.61
    //----
    -0.61
    POSITIVE LOGITS
     maneu
    1.69
     accla
    1.60
     increa
    1.57
     stockholm
    1.46
     unlaw
    1.45
     affor
    1.43
     disagre
    1.42
     scrat
    1.42
     impra
    1.42
     perfet
    1.39
    Activations Density 1.372%

    No Known Activations