© 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. 13761
    Prev
    Next
    INDEX
    Explanations

    references to political structures and processes

    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
    604
    +0.18
    0.6%
    872
    +0.17
    0.6%
    1741
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.18
    0.06
    1288
    +0.17
    0.05
    921
    +0.15
    0.02
    Negative Logits
     sovere
    -1.02
     inev
    -1.01
     guarante
    -0.98
     uniqu
    -0.97
     reluct
    -0.95
     hcm
    -0.93
     disagre
    -0.92
     maneu
    -0.91
     perfon
    -0.91
     coö
    -0.91
    POSITIVE LOGITS
    CROSSTALK
    0.63
     arată
    0.53
    APPLAUSE
    0.52
     argument
    0.51
    Comentários
    0.51
    település
    0.51
    DataPropertyName
    0.50
     wikipagina
    0.49
    calciatore
    0.49
    Πηγή
    0.49
    Activations Density 0.279%

    No Known Activations