© 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. 12873
    Prev
    Next
    INDEX
    Explanations

    information related to geopolitical events and international relations

    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
    1978
    +0.12
    0.3%
    1967
    +0.08
    0.2%
    1484
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.12
    0.05
    776
    +0.08
    0.05
    1878
    +0.07
    0.05
    Negative Logits
     indestru
    -0.91
     hentai
    -0.90
     impra
    -0.88
     unspeak
    -0.86
     unden
    -0.86
     waifu
    -0.85
     horrend
    -0.81
     upvoted
    -0.80
     userType
    -0.80
     intersper
    -0.79
    POSITIVE LOGITS
     kafe
    0.83
     tenda
    0.79
     lampa
    0.78
     alkoh
    0.77
     teras
    0.77
     optik
    0.76
     silikon
    0.76
     tille
    0.75
     lemp
    0.74
     eko
    0.74
    Activations Density 0.183%

    No Known Activations