© 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. 1535
    Prev
    Next
    INDEX
    Explanations

    information related to musical albums and artists

    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
    2011
    +0.08
    0.2%
    1651
    +0.08
    0.2%
    120
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.08
    283
    +0.08
    0.02
    1363
    +0.07
    0.05
    Negative Logits
    <bos>
    -1.22
     thu
    -1.00
    esModule
    -0.93
     mit
    -0.91
    Си
    -0.91
    ActionPerformed
    -0.91
    currentColor
    -0.89
     die
    -0.89
     pro
    -0.89
    局
    -0.88
    POSITIVE LOGITS
     increa
    3.83
     maneu
    3.79
     impra
    3.63
     depic
    3.60
     reluct
    3.59
     guarante
    3.56
     emphat
    3.56
     disagre
    3.51
     fuf
    3.48
     scrat
    3.44
    Activations Density 0.444%

    No Known Activations