© 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. 2152
    Prev
    Next
    INDEX
    Explanations

    phrases describing something as invaluable or irreplaceable

    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
    1823
    +0.07
    0.2%
    1942
    +0.07
    0.2%
    31
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.07
    0.04
    283
    +0.07
    0.01
    1343
    +0.07
    0.04
    Negative Logits
     cabrio
    -0.78
     simplif
    -0.77
     sportback
    -0.71
     affor
    -0.70
     quoique
    -0.70
     rafra
    -0.69
     remet
    -0.68
     cabriolet
    -0.68
     cushi
    -0.67
     lamborghini
    -0.67
    POSITIVE LOGITS
    eless
    1.87
    olds
    1.40
    ELESS
    1.11
     olds
    0.77
    seless
    0.77
    eline
    0.72
    OLDS
    0.68
     Biz
    0.67
    eness
    0.66
    IntoConstraints
    0.63
    Activations Density 0.294%

    No Known Activations