© 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. 2162
    Prev
    Next
    INDEX
    Explanations

    references to futuristic or catastrophic scenarios involving human populations or species

    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
    2015
    +0.18
    0.6%
    1871
    +0.12
    0.4%
    1253
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1650
    +0.18
    0.05
    1489
    +0.12
    0.06
    1380
    +0.12
    0.02
    Negative Logits
     mikrofon
    -1.03
     karton
    -1.00
     alkoh
    -1.00
     praktik
    -0.98
     kompati
    -0.94
     kosme
    -0.93
     pixabay
    -0.91
     optik
    -0.91
     kriminal
    -0.90
     konkre
    -0.90
    POSITIVE LOGITS
    ⓧ
    0.77
     humanity
    0.69
     mankind
    0.69
    ankind
    0.65
    NSUserDefaults
    0.63
     humans
    0.63
     heapq
    0.62
    Життєпис
    0.61
     civilization
    0.60
     sapiens
    0.59
    Activations Density 1.072%

    No Known Activations