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

    Neuronpedia

    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. 4319
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal battles or conflicts and military actions

    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
    198
    +0.08
    0.2%
    1899
    +0.08
    0.2%
    604
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1219
    +0.08
    0.05
    1330
    +0.08
    0.03
    436
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.71
    ">//
    -0.63
    __;
    -0.63
    InitVars
    -0.63
    BeginInit
    -0.62
    ，
    -0.61
    pexpr
    -0.60
    ；
    -0.60
    
    -0.59
    表
    -0.58
    POSITIVE LOGITS
     reluct
    1.93
     encomp
    1.91
     wherea
    1.89
     pamph
    1.87
     increa
    1.86
     fortn
    1.86
     volunte
    1.85
     impra
    1.85
     disagre
    1.84
     secon
    1.84
    Activations Density 0.388%

    No Known Activations