© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5504
    Prev
    Next
    INDEX
    Explanations

    information related to regulatory environments and medical effects, as well as health-related terms like nutrition and calories

    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
    +0.22
    0.7%
    1042
    +0.14
    0.5%
    1741
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.22
    0.06
    2044
    +0.14
    0.13
    468
    +0.11
    0.07
    Negative Logits
     voleva
    -0.96
     faceva
    -0.95
     scopri
    -0.95
     parteci
    -0.90
     facciamo
    -0.89
     vuol
    -0.89
     doveva
    -0.89
     vediamo
    -0.88
     succede
    -0.88
     poteva
    -0.88
    POSITIVE LOGITS
     and
    1.23
     và
    1.01
     indestru
    0.98
     и
    0.96
     inext
    0.96
     inconce
    0.92
     cuck
    0.89
     $\&$
    0.88
    และ
    0.88
     outlander
    0.85
    Activations Density 2.286%

    No Known Activations