© 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. 12798
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to features and functionality of a specific product

    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
    1385
    +0.15
    0.5%
    1842
    +0.14
    0.4%
    1577
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.15
    0.04
    690
    +0.14
    0.03
    2044
    +0.11
    0.06
    Negative Logits
     emphat
    -1.38
     accla
    -1.33
     ?...
    -1.32
     pessi
    -1.32
     embra
    -1.31
     wien
    -1.30
     secon
    -1.28
     ivi
    -1.27
     Cfr
    -1.25
     overla
    -1.25
    POSITIVE LOGITS
     automatically
    0.69
     instantly
    0.64
     upon
    0.63
     toată
    0.63
     diferite
    0.60
    embroidered
    0.58
     functions
    0.58
     câte
    0.57
    glTranslatef
    0.57
     function
    0.57
    Activations Density 0.442%

    No Known Activations