© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12991
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to astronomy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1385
    +0.13
    0.4%
    906
    +0.12
    0.4%
    1661
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.13
    0.03
    191
    +0.12
    0.04
    1661
    +0.12
    0.04
    Negative Logits
     accla
    -0.86
     depic
    -0.83
     reluct
    -0.83
     disagre
    -0.81
     encomp
    -0.80
     inev
    -0.79
     embra
    -0.78
     shenan
    -0.76
     unve
    -0.74
     saar
    -0.74
    POSITIVE LOGITS
     Earth
    0.53
     $_[
    0.53
     earth
    0.48
     orbit
    0.47
     orbital
    0.46
     rotation
    0.46
    }}$\\
    0.44
     planets
    0.44
    Earth
    0.43
     tourisme
    0.43
    Activations Density 0.376%

    No Known Activations