© 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. 13691
    Prev
    Next
    INDEX
    Explanations

    words related to security and hierarchy

    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
    +0.11
    0.3%
    1839
    +0.09
    0.3%
    1535
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.11
    0.04
    300
    +0.09
    0.07
    124
    +0.08
    0.05
    Negative Logits
     BIBSYS
    -0.77
    braith
    -0.72
     userSchema
    -0.66
     تضيفلها
    -0.65
     ProductService
    -0.61
     strto
    -0.61
    ulaski
    -0.59
     ApiService
    -0.58
    eclamp
    -0.58
    astricht
    -0.58
    POSITIVE LOGITS
    tldr
    0.80
     viendra
    0.74
     prendra
    0.59
     eût
    0.58
     Ename
    0.58
     ouvre
    0.57
    Derp
    0.57
     aspect
    0.56
    Yeet
    0.55
     ferait
    0.55
    Activations Density 0.468%

    No Known Activations