© 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. 13040
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and events in the past

    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
    1473
    +0.10
    0.3%
    1812
    +0.07
    0.2%
    1978
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.10
    0.02
    1696
    +0.07
    0.02
    1183
    +0.07
    0.03
    Negative Logits
     teras
    -0.98
     kram
    -0.89
     lemp
    -0.83
     ananas
    -0.83
     Nö
    -0.77
     lele
    -0.76
     persil
    -0.76
     makro
    -0.73
     trico
    -0.72
     Nü
    -0.70
    POSITIVE LOGITS
     is
    0.77
     isn
    0.72
     corresponds
    0.72
     consists
    0.71
     differs
    0.71
     resembles
    0.70
     cannot
    0.68
     depends
    0.68
     represents
    0.67
     belongs
    0.67
    Activations Density 0.360%

    No Known Activations