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

    Neuronpedia

    Jacobian LensNEW
    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. 11774
    Prev
    Next
    INDEX
    Explanations

    mentions of software libraries and code-related terms

    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
    876
    +0.26
    0.8%
    227
    +0.18
    0.6%
    678
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.26
    0.06
    876
    +0.18
    -0.01
    227
    +0.13
    0.06
    Negative Logits
    Trayectoria
    -1.01
    Tē
    -0.90
    InSection
    -0.87
    IsContent
    -0.86
    EndContext
    -0.85
    IActionResult
    -0.85
    Economía
    -0.83
    CompleteListener
    -0.83
    jupiter
    -0.82
    <bos>
    -0.82
    POSITIVE LOGITS
     scrat
    2.38
     guarante
    2.25
     affor
    2.21
     maneu
    2.19
     increa
    2.19
     suscep
    2.18
     inev
    2.16
     intermitt
    2.16
     attemp
    2.15
     overla
    2.14
    Activations Density 0.384%

    No Known Activations