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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12421
    Prev
    Next
    INDEX
    Explanations

    names of people and locations mentioned together with actions they are doing

    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
    184
    +0.23
    0.7%
    1343
    +0.13
    0.4%
    227
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    54
    +0.23
    0.03
    1093
    +0.13
    0.03
    184
    +0.11
    0.01
    Negative Logits
     soggior
    -0.65
     ristor
    -0.60
     labi
    -0.59
     tanong
    -0.58
     pagkak
    -0.57
     visitare
    -0.57
    󠁢
    -0.57
     lasciato
    -0.57
     sostanza
    -0.56
     accogli
    -0.56
    POSITIVE LOGITS
     intersper
    1.24
     unspeak
    1.08
     apprehen
    1.03
     endeavouring
    1.00
     intrigu
    0.98
     shenan
    0.97
     reluct
    0.96
     endeav
    0.96
     impelled
    0.95
     pamph
    0.94
    Activations Density 0.172%

    No Known Activations