© 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. 1129
    Prev
    Next
    INDEX
    Explanations

    emphatic expressions and punctuation marks indicating excitement or urgency

    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
    1044
    +0.15
    0.8%
    1265
    +0.14
    0.7%
    1937
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.15
    0.05
    1343
    +0.14
    0.06
    478
    +0.13
    0.02
    Negative Logits
    <bos>
    -0.87
    FormBorderStyle
    -0.59
     dragón
    -0.56
    clearpage
    -0.55
     ['',
    -0.53
    GroupLayout
    -0.53
    EndProject
    -0.52
    complexContent
    -0.52
     [''],
    -0.51
    queryInterface
    -0.50
    POSITIVE LOGITS
     bandeau
    0.88
     lej
    0.74
    YMMV
    0.72
     !
    0.70
     cushi
    0.69
    Teb
    0.68
    umblr
    0.68
    æus
    0.66
     eyel
    0.66
    karet
    0.65
    Activations Density 0.668%

    No Known Activations