© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 952
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    464
    +0.08
    0.2%
    1167
    +0.07
    0.2%
    2030
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.03
    304
    +0.07
    0.03
    1343
    +0.07
    0.05
    Negative Logits
     (
    -0.81
     
    -0.79
     are
    -0.79
     a
    -0.78
    :
    -0.76
    /
    -0.73
     "
    -0.72
     get
    -0.72
     is
    -0.71
     “
    -0.71
    POSITIVE LOGITS
     silikon
    1.65
     karton
    1.62
     antik
    1.59
     alkoh
    1.57
     nece
    1.50
     keramik
    1.50
     mikrofon
    1.49
     paff
    1.48
     Meksi
    1.47
     kompati
    1.46
    Activations Density 0.277%

    No Known Activations