© 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. 6575
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal or historical contexts

    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
    1264
    +0.13
    0.4%
    674
    +0.10
    0.3%
    1965
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.13
    0.07
    1264
    +0.10
    0.06
    1852
    +0.09
    0.05
    Negative Logits
    .
    -0.90
    ,
    -0.90
     and
    -0.83
     in
    -0.83
     to
    -0.82
    :
    -0.81
     (
    -0.81
    !
    -0.80
     for
    -0.80
     
    -0.80
    POSITIVE LOGITS
     sappi
    2.34
     affez
    2.28
     soggior
    2.26
     dispen
    2.19
     tranquillo
    2.15
     abbra
    2.14
     dises
    2.12
     tramont
    2.10
     imposs
    2.10
     nutr
    2.09
    Activations Density 0.271%

    No Known Activations