© 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. 12990
    Prev
    Next
    INDEX
    Explanations

    words related to surveillance, data privacy, and technology

    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
    517
    +0.19
    0.8%
    896
    +0.16
    0.7%
    1624
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.19
    0.04
    896
    +0.16
    0.03
    1624
    +0.15
    0.04
    Negative Logits
     Mesmo
    -0.76
     Muitos
    -0.68
     Embora
    -0.65
    Mesmo
    -0.63
     Qualquer
    -0.61
     Portanto
    -0.60
    Alguns
    -0.60
     Ainda
    -0.60
     Hoje
    -0.59
    Apesar
    -0.58
    POSITIVE LOGITS
     fta
    1.25
     vns
    1.23
     fup
    1.19
     squa
    1.17
     invin
    1.14
     poff
    1.14
     ftu
    1.13
     blos
    1.13
     aen
    1.13
     fep
    1.12
    Activations Density 0.211%

    No Known Activations