© 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. 14433
    Prev
    Next
    INDEX
    Explanations

    references to people or individuals

    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
    25
    +0.13
    0.5%
    1978
    +0.13
    0.4%
    1510
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.13
    0.07
    874
    +0.13
    0.06
    851
    +0.12
    0.05
    Negative Logits
     maroc
    -0.94
     umo
    -0.89
     bonjour
    -0.88
     répon
    -0.88
     poliester
    -0.88
     ordina
    -0.88
     milano
    -0.88
     simplif
    -0.86
     bandung
    -0.86
     sopr
    -0.86
    POSITIVE LOGITS
    people
    0.97
     people
    0.96
    People
    0.88
     People
    0.87
    PEOPLE
    0.79
     PEOPLE
    0.78
     person
    0.70
     folks
    0.66
     who
    0.65
     peoples
    0.64
    Activations Density 0.126%

    No Known Activations