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

    Neuronpedia

    Jacobian LensNEW
    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. 5960
    Prev
    Next
    INDEX
    Explanations

    instances when individuals realize or recognize something

    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
    1265
    +0.14
    0.5%
    1482
    +0.12
    0.4%
    1983
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    991
    +0.14
    0.03
    1482
    +0.12
    0.03
    1983
    +0.12
    0.03
    Negative Logits
     Áng
    -0.69
     viciss
    -0.65
     exé
    -0.65
     mikrofon
    -0.64
     patrio
    -0.63
     keramik
    -0.62
     Examin
    -0.61
     robus
    -0.60
     ausp
    -0.59
    $+\
    -0.58
    POSITIVE LOGITS
     realize
    1.13
     realized
    1.03
     realise
    1.02
     realizes
    0.98
     realizing
    0.96
     realization
    0.94
     realised
    0.91
     realises
    0.85
     realising
    0.83
     realiz
    0.81
    Activations Density 0.068%

    No Known Activations