© 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. 2457
    Prev
    Next
    INDEX
    Explanations

    terms related to requirements or obligations

    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
    1339
    +0.14
    0.5%
    1677
    +0.12
    0.4%
    241
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.14
    0.03
    1339
    +0.12
    0.03
    420
    +0.12
    0.03
    Negative Logits
     suspic
    -0.74
     impractica
    -0.72
     pessi
    -0.68
     disgra
    -0.64
     unlaw
    -0.64
     emphat
    -0.64
     robus
    -0.62
     Theile
    -0.62
     laun
    -0.62
     resear
    -0.62
    POSITIVE LOGITS
     requirement
    0.97
    required
    0.95
     required
    0.94
     requirements
    0.93
    Required
    0.91
     Required
    0.90
    require
    0.87
     require
    0.86
    Require
    0.86
     Requirements
    0.85
    Activations Density 0.078%

    No Known Activations