© 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. 233
    Prev
    Next
    INDEX
    Explanations

    the word "verb" in sentences

    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
    1137
    +0.10
    0.3%
    1983
    +0.08
    0.2%
    1654
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.04
    1896
    +0.08
    0.02
    783
    +0.07
    0.03
    Negative Logits
     balas
    -0.66
     monta
    -0.61
     mals
    -0.61
     elit
    -0.60
     malu
    -0.59
    contentLoaded
    -0.57
    KY
    -0.57
    bolista
    -0.57
     rada
    -0.55
     Tur
    -0.54
    POSITIVE LOGITS
     verb
    1.93
     verbs
    1.66
     Verbs
    1.54
     noun
    1.40
    verb
    1.36
     ecru
    1.31
     appunt
    1.31
     Verb
    1.30
    Verb
    1.28
     affez
    1.22
    Activations Density 0.301%

    No Known Activations