© 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. 12908
    Prev
    Next
    INDEX
    Explanations

    policy recommendations related to governance, corruption, human rights, economic policies, and infrastructure development

    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
    184
    +0.16
    0.5%
    1343
    +0.14
    0.5%
    1385
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.16
    0.04
    1499
    +0.14
    0.04
    184
    +0.12
    0.01
    Negative Logits
     reluct
    -0.75
     practition
    -0.73
     indoc
    -0.70
     divisi
    -0.69
     emphat
    -0.69
     frivol
    -0.69
     pamph
    -0.69
     belliger
    -0.68
     apprehen
    -0.68
     sarcas
    -0.67
    POSITIVE LOGITS
     morfo
    0.94
     moza
    0.91
     fosfor
    0.88
     pól
    0.87
     torba
    0.85
     raste
    0.83
     teras
    0.82
     rente
    0.82
     meras
    0.82
     antik
    0.81
    Activations Density 0.207%

    No Known Activations