© 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. 3415
    Prev
    Next
    INDEX
    Explanations

    origins of mythical creatures or historical beliefs

    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
    50
    +0.24
    0.8%
    2015
    +0.15
    0.5%
    906
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1959
    +0.24
    0.12
    1415
    +0.15
    0.04
    16
    +0.14
    0.10
    Negative Logits
    GraphicsUnit
    -0.69
    TagMode
    -0.66
    BeginInit
    -0.66
    AddTagHelper
    -0.66
     Audiodateien
    -0.62
    ‌.
    -0.62
     ***!
    -0.62
    HtmlAttribute
    -0.61
    ─
    -0.61
     chi̍t
    -0.61
    POSITIVE LOGITS
     swarovski
    1.89
     disagre
    1.87
     unlaw
    1.84
     pamph
    1.83
     hairc
    1.82
     encomp
    1.80
     reluct
    1.79
     shenan
    1.77
     intersper
    1.76
     unspeak
    1.72
    Activations Density 1.613%

    No Known Activations