© 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. 1613
    Prev
    Next
    INDEX
    Explanations

    product categories related to children, such as gifts, books, and toys

    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
    1677
    +0.08
    0.2%
    50
    +0.07
    0.2%
    190
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.03
    283
    +0.07
    0.01
    483
    +0.07
    0.02
    Negative Logits
     etmeye
    -0.93
     ediyor
    -0.73
    einem
    -0.63
     etme
    -0.61
    ďaka
    -0.57
    }{||
    -0.53
     fået
    -0.53
     terminate
    -0.53
     ettiği
    -0.53
     suspend
    -0.52
    POSITIVE LOGITS
    ets
    2.40
    et
    2.08
    ETS
    1.72
    ET
    1.66
    eting
    1.24
     véhic
    1.10
     catég
    1.07
     effe
    1.07
    etl
    1.05
     guarante
    1.05
    Activations Density 0.159%

    No Known Activations