© 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. 1275
    Prev
    Next
    INDEX
    Explanations

    mentions of the planet Mars in texts related to space exploration, scientific research, and fictional narratives

    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
    1178
    +0.14
    0.4%
    1480
    +0.09
    0.3%
    1328
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.14
    0.03
    1120
    +0.09
    0.02
    1178
    +0.09
    0.02
    Negative Logits
    <bos>
    -0.73
    и
    -0.63
     regulate
    -0.63
     prepare
    -0.61
     do
    -0.61
     ال
    -0.61
     expand
    -0.61
    <eos>
    -0.60
     prevent
    -0.60
    образова
    -0.60
    POSITIVE LOGITS
     Mars
    2.42
    Mars
    2.19
     MARS
    2.02
     mars
    1.84
     Marte
    1.54
    mars
    1.53
     meis
    1.39
     sappi
    1.38
     jupiter
    1.37
     stockholm
    1.35
    Activations Density 0.177%

    No Known Activations