© 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. 6970
    Prev
    Next
    INDEX
    Explanations

    names of specific newspapers or media outlets

    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
    1150
    +0.11
    0.3%
    227
    +0.09
    0.3%
    964
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1997
    +0.11
    0.05
    1652
    +0.09
    0.04
    648
    +0.09
    0.04
    Negative Logits
     fluo
    -1.06
     aen
    -0.98
     erec
    -0.96
     napoli
    -0.94
     meis
    -0.93
     aquarelle
    -0.93
     Octobre
    -0.91
     uncin
    -0.91
     unce
    -0.91
     effe
    -0.90
    POSITIVE LOGITS
     newspaper
    0.80
     newspapers
    0.60
     Newspaper
    0.56
     Zeitung
    0.54
     Times
    0.54
     Daily
    0.53
     paper
    0.52
    newspaper
    0.51
     pprint
    0.51
     reporter
    0.51
    Activations Density 0.140%

    No Known Activations