© 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. 3798
    Prev
    Next
    INDEX
    Explanations

    discussions related to broadcasting, political systems, and technological advancements

    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
    474
    +0.09
    0.3%
    468
    +0.08
    0.2%
    876
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.09
    0.05
    2030
    +0.08
    0.03
    1864
    +0.07
    0.04
    Negative Logits
     increa
    -1.90
     disagre
    -1.90
     impra
    -1.89
     reluct
    -1.88
     intersper
    -1.84
     unspeak
    -1.82
     depic
    -1.79
     affor
    -1.78
     encomp
    -1.78
     fortn
    -1.75
    POSITIVE LOGITS
     thing
    0.93
     way
    0.88
     option
    0.78
     source
    0.78
     reason
    0.78
     aspect
    0.73
     noten
    0.73
     tool
    0.72
     method
    0.69
     obst
    0.69
    Activations Density 0.318%

    No Known Activations