© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1632
    Prev
    Next
    INDEX
    Explanations

    mentions of fast-paced action or excitement

    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
    1120
    +0.09
    0.3%
    1336
    +0.08
    0.3%
    617
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.09
    0.04
    1343
    +0.08
    0.11
    1120
    +0.06
    0.10
    Negative Logits
    ,
    -1.07
    .
    -1.05
     can
    -1.05
     for
    -1.02
     in
    -1.02
     but
    -1.02
     to
    -1.02
     put
    -1.02
     
    -1.01
    :
    -1.01
    POSITIVE LOGITS
     wien
    2.96
     franz
    2.94
     dispen
    2.91
     meis
    2.87
     effe
    2.86
     inder
    2.85
     grati
    2.85
     fatis
    2.81
     ordina
    2.73
     socie
    2.73
    Activations Density 1.292%

    No Known Activations