© 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. 14873
    Prev
    Next
    INDEX
    Explanations

    instances where a specific term or name is mentioned

    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
    776
    +0.15
    0.5%
    50
    +0.15
    0.5%
    382
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.15
    0.09
    16
    +0.15
    0.09
    1896
    +0.12
    0.05
    Negative Logits
     tramonto
    -1.06
     medesimo
    -1.02
     delà
    -0.95
     signore
    -0.95
     gardien
    -0.89
     créateur
    -0.87
     vainqueur
    -0.86
     mattino
    -0.86
     giudice
    -0.85
     silenzio
    -0.84
    POSITIVE LOGITS
    Sklici
    0.76
     barran
    0.68
    Flere
    0.67
     dozen
    0.67
    Glej
    0.67
    Pä
    0.66
    তথ্যসূত্র
    0.65
    dozen
    0.65
    astéro
    0.64
     handful
    0.64
    Activations Density 0.515%

    No Known Activations