© 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. 13627
    Prev
    Next
    INDEX
    Explanations

    declarations or statements suggesting permanence or perpetuity

    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
    1904
    +0.11
    0.3%
    1661
    +0.09
    0.3%
    1962
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.04
    1904
    +0.09
    0.05
    1661
    +0.07
    0.03
    Negative Logits
     unan
    -0.50
     Messieurs
    -0.49
     intit
    -0.49
     ausp
    -0.48
     igno
    -0.47
     DBNull
    -0.46
     supplé
    -0.46
     déterminé
    -0.45
     Ilustra
    -0.45
     Dés
    -0.45
    POSITIVE LOGITS
     longevity
    0.90
     permanence
    0.89
     perpetuity
    0.88
     permanent
    0.80
     continual
    0.80
     perpetually
    0.79
     lasting
    0.79
     continually
    0.77
     continuously
    0.76
     perpetual
    0.76
    Activations Density 1.138%

    No Known Activations