© 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. 13786
    Prev
    Next
    INDEX
    Explanations

    phrases related to data analysis and statistics

    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
    1870
    +0.14
    0.4%
    1839
    +0.09
    0.3%
    1415
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.14
    0.03
    563
    +0.09
    0.03
    245
    +0.08
    0.02
    Negative Logits
    tuu
    -0.55
    ikiki
    -0.55
     esternos
    -0.53
     Meksiku
    -0.53
     Pines
    -0.50
    uuuuu
    -0.50
    Datuak
    -0.49
    qas
    -0.49
     Briefs
    -0.48
     архивлан
    -0.47
    POSITIVE LOGITS
    greja
    0.73
     Qualquer
    0.71
    Cringe
    0.69
    Noice
    0.68
    Lmfao
    0.68
     ajuns
    0.68
     deschis
    0.68
     Portanto
    0.67
    Ikr
    0.66
    FTFY
    0.66
    Activations Density 0.320%

    No Known Activations