© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4267
    Prev
    Next
    INDEX
    Explanations

    names of people or organizations along with associated titles or roles

    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
    814
    +0.14
    0.5%
    1805
    +0.14
    0.5%
    501
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1805
    +0.14
    0.03
    501
    +0.14
    0.04
    814
    +0.13
    0.03
    Negative Logits
     grazia
    -0.46
    dinga
    -0.43
    tedì
    -0.41
    idelberg
    -0.38
     Regione
    -0.38
    kawi
    -0.38
     clinica
    -0.37
     AspNetCore
    -0.37
     alcanza
    -0.37
    dients
    -0.36
    POSITIVE LOGITS
     Sol
    0.76
     gsx
    0.76
     SOL
    0.74
     isuzu
    0.73
    Sol
    0.73
     Soli
    0.71
     sol
    0.70
     pajero
    0.68
     solen
    0.67
     sergio
    0.67
    Activations Density 0.274%

    No Known Activations