© 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. 7628
    Prev
    Next
    INDEX
    Explanations

    scientific or medical terms, potentially related to research findings or methods

    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
    1343
    +0.24
    0.8%
    605
    +0.15
    0.5%
    478
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.24
    0.03
    536
    +0.15
    0.02
    605
    +0.15
    0.01
    Negative Logits
    ,
    -0.87
     and
    -0.83
     et
    -0.83
     (
    -0.82
     up
    -0.80
     —
    -0.80
     for
    -0.80
    -
    -0.79
     of
    -0.79
     ter
    -0.78
    POSITIVE LOGITS
     ftu
    2.75
     fta
    2.62
     fto
    2.60
     effe
    2.58
     squa
    2.55
     stockholm
    2.53
     inev
    2.53
     increa
    2.51
     fuf
    2.50
     vns
    2.50
    Activations Density 0.088%

    No Known Activations