© 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. 3549
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases, historical events, and social issues

    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
    752
    +0.14
    0.4%
    1828
    +0.10
    0.3%
    1350
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.14
    0.06
    752
    +0.10
    0.05
    1828
    +0.09
    0.05
    Negative Logits
     respek
    -0.67
     klap
    -0.65
     kontinu
    -0.65
     kompati
    -0.63
     komfort
    -0.61
     kokos
    -0.58
     respekt
    -0.58
     komplet
    -0.56
     kosme
    -0.54
     gema
    -0.53
    POSITIVE LOGITS
     Áng
    1.05
     Chá
    1.04
     endom
    1.03
     hcm
    0.88
     sergio
    0.87
     Darío
    0.85
     Fait
    0.85
     santiago
    0.84
     jorge
    0.83
     Juf
    0.83
    Activations Density 0.308%

    No Known Activations