© 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. 14246
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific topics, specifically orbit configurations, atmospheric composition, and historical events

    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
    1839
    +0.12
    0.4%
    674
    +0.11
    0.4%
    144
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.12
    0.03
    1491
    +0.11
    0.03
    1828
    +0.11
    0.03
    Negative Logits
     Kün
    -0.59
     Diony
    -0.56
     inext
    -0.56
     abstrait
    -0.54
     uninten
    -0.52
     perfet
    -0.51
     increa
    -0.51
     Gonz
    -0.50
     Etr
    -0.50
     deleter
    -0.50
    POSITIVE LOGITS
    <bos>
    0.81
     huwa
    0.56
     utaf
    0.54
     ikiwa
    0.52
    беріга
    0.49
    ometrial
    0.49
     Савезне
    0.47
    ഢ
    0.46
     nagu
    0.45
    ئيس
    0.43
    Activations Density 0.111%

    No Known Activations