© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4462
    Prev
    Next
    INDEX
    Explanations

    dates and events related to sports games, as well as technology-related content

    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
    856
    +0.22
    0.8%
    394
    +0.18
    0.7%
    998
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1784
    +0.22
    0.03
    856
    +0.18
    0.02
    1157
    +0.11
    0.03
    Negative Logits
    :,,
    -0.66
    YMMV
    -0.65
     fta
    -0.65
    «<
    -0.64
     ftre
    -0.64
     tupperware
    -0.64
     vost
    -0.63
     poft
    -0.62
     oleo
    -0.62
     „,
    -0.61
    POSITIVE LOGITS
    IVEREF
    0.62
    __':
    0.61
    RTEE
    0.54
    AutoScaleMode
    0.51
    Bibliograf
    0.49
    webElementXpaths
    0.48
    تقاوى
    0.47
     الحره
    0.46
     Audiodateien
    0.46
    Datuak
    0.41
    Activations Density 0.270%

    No Known Activations