© 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. 1035
    Prev
    Next
    INDEX
    Explanations

    mentions of names of buildings, landmarks, locations, and events

    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
    1472
    +0.11
    0.3%
    1343
    +0.10
    0.3%
    1013
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.11
    0.04
    964
    +0.10
    0.03
    1562
    +0.10
    0.03
    Negative Logits
     ridu
    -0.89
     affez
    -0.89
     peculi
    -0.88
     sacerd
    -0.87
     sappi
    -0.81
     rispond
    -0.81
     felici
    -0.80
     dimentic
    -0.79
     coö
    -0.78
     disreg
    -0.77
    POSITIVE LOGITS
     Saint
    0.75
     Saints
    0.68
     saint
    0.59
     St
    0.58
    Saint
    0.58
     saints
    0.56
    saint
    0.52
    Saints
    0.48
     Stan
    0.47
     Street
    0.46
    Activations Density 0.141%

    No Known Activations