© 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. 2078
    Prev
    Next
    INDEX
    Explanations

    economic and industry-related information, particularly focusing on prices and energy sources

    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
    544
    +0.08
    0.3%
    1296
    +0.08
    0.3%
    241
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.08
    0.03
    283
    +0.08
    0.01
    180
    +0.08
    0.03
    Negative Logits
     intersper
    -1.13
     McLaugh
    -1.12
     enshr
    -1.03
     Daven
    -1.03
     vainly
    -1.02
     renounced
    -0.98
     shenan
    -0.98
     McInt
    -0.96
     chanced
    -0.95
     Middles
    -0.95
    POSITIVE LOGITS
    $
    1.57
    -$
    1.34
    +$
    1.15
    $-
    1.14
    $)
    1.11
    ]$
    1.11
    $"
    1.08
    :$
    1.04
     tenda
    1.04
    $',
    1.04
    Activations Density 0.306%

    No Known Activations