© 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. 1844
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms

    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
    1870
    +0.15
    0.4%
    1385
    +0.11
    0.3%
    468
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2041
    +0.15
    0.06
    1870
    +0.11
    0.04
    1317
    +0.11
    0.05
    Negative Logits
     dispen
    -0.68
     solidar
    -0.64
     ciao
    -0.63
     embra
    -0.63
     provar
    -0.61
     lancia
    -0.60
     bonjour
    -0.60
     batte
    -0.60
     chevalier
    -0.59
     disting
    -0.59
    POSITIVE LOGITS
    genicity
    0.61
     jawa
    0.61
     papilla
    0.58
     and
    0.57
    jména
    0.56
    letterSpacing
    0.55
     utford
    0.54
    ométrie
    0.52
    ásra
    0.51
     sentito
    0.50
    Activations Density 0.439%

    No Known Activations