© 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. 2242
    Prev
    Next
    INDEX
    Explanations

    descriptions of the composition of objects or groups

    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
    75
    +0.12
    0.4%
    976
    +0.11
    0.4%
    1363
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    976
    +0.12
    0.02
    75
    +0.11
    0.02
    169
    +0.11
    0.02
    Negative Logits
    Cdt
    -0.45
    Dowell
    -0.43
     NLI
    -0.41
    jobs
    -0.40
    Ney
    -0.39
    SqlDataReader
    -0.39
    NewLabel
    -0.39
    Jobs
    -0.38
    tbx
    -0.37
    Dod
    -0.37
    POSITIVE LOGITS
     consisted
    1.01
     consist
    0.99
     consists
    0.97
     muna
    0.96
     loob
    0.93
     consisting
    0.92
     sarili
    0.91
     tanong
    0.88
     panahon
    0.83
     kasama
    0.83
    Activations Density 0.067%

    No Known Activations