© 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. 12747
    Prev
    Next
    INDEX
    Explanations

    technical information and descriptions of mechanical operations or systems

    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
    1865
    +0.14
    0.5%
    1472
    +0.13
    0.5%
    795
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1472
    +0.14
    0.06
    795
    +0.13
    0.04
    1520
    +0.12
    0.05
    Negative Logits
     تانيه
    -0.61
     gyhoeddwyd
    -0.59
     مرئيه
    -0.58
    DisplayMetrics
    -0.56
    ManagedBean
    -0.55
    --)
    -0.54
    hintText
    -0.53
    Tikang
    -0.52
    кобрита
    -0.52
     tích
    -0.51
    POSITIVE LOGITS
     effe
    1.53
     paff
    1.45
     ftu
    1.44
     emphat
    1.44
     milf
    1.43
     inev
    1.41
     perfet
    1.40
     increa
    1.40
     fta
    1.37
     stockholm
    1.36
    Activations Density 0.207%

    No Known Activations