© 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. 0-RES-JB
    11. 366
    Prev
    Next
    INDEX
    Explanations

    names of mythological figures

    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
    1271
    +0.15
    0.5%
    395
    +0.12
    0.4%
    1187
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.15
    0.08
    1343
    +0.12
    0.07
    690
    +0.11
    0.07
    Negative Logits
    <bos>
    -0.84
     hjæl
    -0.67
     kræ
    -0.66
    Пу
    -0.63
     świę
    -0.61
    い
    -0.61
    つ
    -0.60
     arbejde
    -0.60
    bibnamefont
    -0.59
    꺼
    -0.59
    POSITIVE LOGITS
     stockholm
    2.09
     madonna
    2.07
     ?...
    2.04
     emphat
    2.02
     maneu
    2.00
     lidl
    1.96
     wien
    1.96
     reluct
    1.96
     increa
    1.96
     strick
    1.95
    Activations Density 0.401%

    No Known Activations