© 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. 14120
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people and locations related to news events

    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
    1842
    +0.12
    0.3%
    964
    +0.12
    0.3%
    644
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    644
    +0.12
    0.05
    964
    +0.12
    0.04
    498
    +0.08
    0.03
    Negative Logits
     Ename
    -1.18
     swarovski
    -1.18
     embodi
    -1.15
     [''
    -1.09
     encomp
    -1.03
     unden
    -0.98
     scrat
    -0.97
     disreg
    -0.97
     ecru
    -0.97
     toshiba
    -0.97
    POSITIVE LOGITS
     police
    0.56
    Police
    0.56
     Police
    0.54
    police
    0.52
    xnn
    0.51
     >=",
    0.50
    Архівовано
    0.50
    冤
    0.49
     shootings
    0.49
    UnitTesting
    0.48
    Activations Density 0.313%

    No Known Activations