© 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. 3745
    Prev
    Next
    INDEX
    Explanations

    mentions of the technology PostgreSQL and its features

    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
    690
    +0.12
    0.4%
    1403
    +0.12
    0.3%
    678
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1866
    +0.12
    0.05
    1403
    +0.12
    0.02
    918
    +0.11
    0.04
    Negative Logits
     Joaqu
    -0.74
     Marín
    -0.70
    Vaata
    -0.68
     Mónica
    -0.66
    Literat
    -0.65
     Leopoldo
    -0.65
     Mejía
    -0.64
     Darío
    -0.64
     Lázaro
    -0.63
    astéro
    -0.62
    POSITIVE LOGITS
    new
    0.85
     improvements
    0.84
     new
    0.83
     enhancements
    0.76
     Improvements
    0.71
     changes
    0.65
     improved
    0.63
     updates
    0.63
     nieuwe
    0.62
     CHANGES
    0.62
    Activations Density 0.566%

    No Known Activations