© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2398
    Prev
    Next
    INDEX
    Explanations

    information related to statistical data, averages, and analysis within different groups

    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
    1445
    +0.10
    0.3%
    1385
    +0.08
    0.2%
    2036
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2036
    +0.10
    0.03
    1499
    +0.08
    0.04
    1445
    +0.07
    0.04
    Negative Logits
     encomp
    -1.83
     maneu
    -1.73
     wien
    -1.68
     unden
    -1.65
     impra
    -1.65
     strick
    -1.64
     secon
    -1.62
     depic
    -1.62
     snoopy
    -1.61
     shenan
    -1.60
    POSITIVE LOGITS
     average
    0.96
    average
    0.87
    Average
    0.86
     Average
    0.83
    平均
    0.82
     averages
    0.80
     promedio
    0.78
     averaged
    0.76
     averaging
    0.75
     mean
    0.73
    Activations Density 0.170%

    No Known Activations