© 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. 1729
    Prev
    Next
    INDEX
    Explanations

    references to locations and institutions named "Cos" or "Cosmetology"

    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
    966
    +0.11
    0.3%
    871
    +0.08
    0.3%
    699
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    966
    +0.11
    0.02
    1343
    +0.08
    0.02
    1770
    +0.08
    0.01
    Negative Logits
    /**
    -0.67
     близь
    -0.63
    #
    -0.60
    invokeLater
    -0.58
     Україні
    -0.58
     помі
    -0.58
    ResumeLayout
    -0.58
     розта
    -0.58
     розвитку
    -0.57
    RTGC
    -0.57
    POSITIVE LOGITS
     Cos
    2.83
     cos
    2.64
    Cos
    2.64
    cos
    2.35
     COS
    2.03
    COS
    1.94
     maneu
    1.62
     impra
    1.60
     depic
    1.60
     cosine
    1.59
    Activations Density 0.193%

    No Known Activations