© 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. 2031
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications, certifications, and standards

    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
    1937
    +0.10
    0.3%
    1376
    +0.08
    0.3%
    568
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.02
    568
    +0.08
    0.02
    1343
    +0.08
    0.02
    Negative Logits
     once
    -0.65
     enter
    -0.63
     can
    -0.63
    public
    -0.63
     get
    -0.63
     take
    -0.62
    ,
    -0.61
     there
    -0.61
     eventually
    -0.61
     took
    -0.61
    POSITIVE LOGITS
     ISO
    2.86
    ISO
    2.67
     iso
    2.31
    iso
    2.00
     Iso
    1.96
    Iso
    1.86
     ftu
    1.58
     affor
    1.57
     fatis
    1.57
     dises
    1.56
    Activations Density 0.220%

    No Known Activations