Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6180
    Prev
    Next
    INDEX
    Explanations

    references to space exploration and specific celestial bodies such as Mars and the Moon

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1909
    +0.18
    1.0%
    1983
    +0.17
    0.9%
    1896
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.18
    0.04
    690
    +0.17
    0.04
    1097
    +0.12
    0.06
    Negative Logits
    vece
    -0.77
     encomp
    -0.75
     intersper
    -0.70
     Septembre
    -0.66
     empêche
    -0.66
     shenan
    -0.65
     préfère
    -0.63
     alip
    -0.62
     contd
    -0.61
     entraîne
    -0.61
    POSITIVE LOGITS
     Mars
    1.12
    Mars
    1.02
     mars
    0.84
    mars
    0.72
     Bark
    0.66
     bark
    0.61
    Hayes
    0.61
     MARS
    0.60
     Hayes
    0.59
    Bark
    0.58
    Activations Density 0.588%

    No Known Activations