© 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. 11796
    Prev
    Next
    INDEX
    Explanations

    legal and political terms and situations

    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
    674
    +0.20
    0.7%
    1577
    +0.18
    0.7%
    198
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.20
    0.04
    137
    +0.18
    0.11
    198
    +0.17
    0.09
    Negative Logits
     Mlle
    -1.23
     impra
    -1.20
     „,
    -1.16
     unden
    -1.15
     michelin
    -1.11
     disagre
    -1.09
     Middles
    -1.08
     Juf
    -1.06
     snoopy
    -1.06
     desir
    -1.04
    POSITIVE LOGITS
    <bos>
    0.94
    ьаж
    0.55
    ActionCreators
    0.55
    TagMode
    0.54
     BoxDecoration
    0.52
    openConnection
    0.52
     AssemblyCompany
    0.50
    IsContent
    0.47
    zzleHttp
    0.47
     climático
    0.46
    Activations Density 2.474%

    No Known Activations