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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1058
    Prev
    Next
    INDEX
    Explanations

    phrases related to political controversy and opposition

    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
    1548
    +0.12
    0.5%
    1328
    +0.11
    0.5%
    1376
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1548
    +0.12
    0.02
    1492
    +0.11
    0.03
    1490
    +0.11
    0.03
    Negative Logits
     kahit
    -0.54
     guma
    -0.53
     asmen
    -0.52
     valsty
    -0.52
     aukš
    -0.52
     noong
    -0.47
     maraming
    -0.46
     ngayon
    -0.46
     habang
    -0.46
     vandens
    -0.46
    POSITIVE LOGITS
     Par
    1.18
     par
    1.13
     PAR
    1.11
    Par
    1.07
    par
    1.07
    PAR
    0.92
     Pars
    0.88
     pars
    0.87
     paras
    0.85
     paral
    0.83
    Activations Density 0.102%

    No Known Activations