© 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. 2234
    Prev
    Next
    INDEX
    Explanations

    words related to commercial establishments, especially shopping malls

    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
    1961
    +0.10
    0.3%
    1480
    +0.09
    0.3%
    517
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1480
    +0.10
    0.03
    817
    +0.09
    0.03
    517
    +0.08
    0.02
    Negative Logits
    <bos>
    -0.61
    切
    -0.55
     įsi
    -0.54
     continue
    -0.53
     bury
    -0.53
     scooped
    -0.52
    せい
    -0.52
     contend
    -0.52
     onto
    -0.51
     rehabilitate
    -0.51
    POSITIVE LOGITS
     Mall
    2.74
     mall
    2.46
    Mall
    2.44
     MALL
    2.10
    mall
    1.83
     malls
    1.75
     dovr
    1.08
     Bibl
    1.01
     sappi
    0.99
     Ottobre
    0.99
    Activations Density 0.151%

    No Known Activations