© 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. 3746
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns followed by some form of evaluation or contemplation

    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
    872
    +0.09
    0.2%
    655
    +0.08
    0.2%
    1604
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.09
    0.03
    62
    +0.08
    0.03
    1812
    +0.07
    0.03
    Negative Logits
     impractica
    -0.95
     Bartholo
    -0.94
     Juf
    -0.92
     Hez
    -0.91
     aen
    -0.90
     !...
    -0.88
     lts
    -0.88
     Eft
    -0.88
     Epif
    -0.87
     stockholm
    -0.86
    POSITIVE LOGITS
     personally
    0.83
     anyway
    0.68
     myself
    0.62
     anyways
    0.61
    AsUp
    0.60
    ofern
    0.57
     persönlich
    0.54
    osoba
    0.54
    VYMaps
    0.53
    ためには
    0.50
    Activations Density 0.129%

    No Known Activations