© 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. 2175
    Prev
    Next
    INDEX
    Explanations

    social and political issues related to society, privacy, and ethical dilemmas

    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
    468
    +0.15
    0.6%
    889
    +0.15
    0.6%
    1077
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    889
    +0.15
    0.04
    636
    +0.15
    0.05
    468
    +0.11
    0.05
    Negative Logits
     alip
    -0.76
     guma
    -0.62
     kuh
    -0.59
     labd
    -0.59
     saad
    -0.59
     uwe
    -0.58
     kuta
    -0.54
     naf
    -0.54
     réguli
    -0.53
     pama
    -0.52
    POSITIVE LOGITS
     issue
    1.36
     issues
    1.30
     Issue
    1.29
    issue
    1.23
     Issues
    1.23
    Issue
    1.22
    Issues
    1.21
    issues
    1.21
     ISSUE
    1.15
     ISSUES
    1.14
    Activations Density 0.086%

    No Known Activations