© 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. 2398
    Prev
    Next
    INDEX
    Explanations

    names of schools or sports teams

    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
    1376
    +0.11
    0.3%
    11
    +0.10
    0.3%
    966
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.11
    0.05
    283
    +0.10
    0.01
    184
    +0.09
    0.02
    Negative Logits
     interse
    -0.87
     antem
    -0.85
    ⓧ
    -0.85
     monot
    -0.84
     nutr
    -0.84
     Aler
    -0.82
     adri
    -0.82
     cryst
    -0.82
     unil
    -0.82
     abel
    -0.81
    POSITIVE LOGITS
    croft
    1.27
     Bennett
    0.79
     grasp
    0.78
    omas
    0.77
     caregivers
    0.73
     caregiver
    0.73
     Hospice
    0.73
     Quinn
    0.67
    Bennett
    0.66
     pony
    0.62
    Activations Density 0.344%

    No Known Activations