© 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. 874
    Prev
    Next
    INDEX
    Explanations

    proper nouns and phrases related to productivity and development

    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
    1919
    +0.11
    0.3%
    227
    +0.10
    0.3%
    872
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.11
    0.06
    227
    +0.10
    0.05
    478
    +0.09
    0.03
    Negative Logits
     lele
    -1.24
     magis
    -1.11
     haup
    -1.11
     pama
    -1.10
     ananas
    -1.10
     kram
    -1.09
     ohr
    -1.09
     hina
    -1.09
     saba
    -1.09
     meis
    -1.09
    POSITIVE LOGITS
     therefore
    0.80
     however
    0.76
     certainly
    0.65
     obviously
    0.65
     could
    0.64
     seems
    0.63
     accordingly
    0.62
     does
    0.61
     took
    0.61
     might
    0.60
    Activations Density 0.347%

    No Known Activations