© 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. 7696
    Prev
    Next
    INDEX
    Explanations

    references to time periods

    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
    1013
    +0.13
    0.4%
    776
    +0.11
    0.3%
    501
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1830
    +0.13
    0.06
    929
    +0.11
    0.04
    220
    +0.11
    0.05
    Negative Logits
     ghe
    -0.80
     sml
    -0.75
     ché
    -0.74
     mme
    -0.72
     espé
    -0.70
     siff
    -0.70
     franz
    -0.70
     meis
    -0.70
     sii
    -0.69
     hcm
    -0.67
    POSITIVE LOGITS
    year
    0.67
     year
    0.61
    month
    0.58
     ago
    0.57
     month
    0.56
    week
    0.48
     week
    0.47
    YEAR
    0.47
     idolat
    0.46
    elfth
    0.46
    Activations Density 0.188%

    No Known Activations