© 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. 13914
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic activities and 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
    2034
    +0.21
    0.6%
    382
    +0.14
    0.4%
    1535
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.21
    0.13
    1917
    +0.14
    0.08
    195
    +0.13
    0.10
    Negative Logits
     guangdong
    -0.73
    Faites
    -0.65
     blusa
    -0.64
    Zdra
    -0.64
    Vrij
    -0.58
    Quiénes
    -0.58
     taget
    -0.57
     quidem
    -0.57
     jums
    -0.57
    えたら
    -0.57
    POSITIVE LOGITS
     wherea
    1.24
     depic
    1.19
     lts
    1.12
     fortn
    1.11
     secon
    1.08
     indestru
    1.07
     Venise
    1.06
     tremb
    1.06
     encomp
    1.05
     fff
    1.03
    Activations Density 0.706%

    No Known Activations