© 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. 14285
    Prev
    Next
    INDEX
    Explanations

    references to technology-related programs and initiatives

    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
    297
    +0.11
    0.3%
    1735
    +0.11
    0.3%
    1965
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1735
    +0.11
    0.05
    2010
    +0.11
    0.05
    990
    +0.09
    0.04
    Negative Logits
     affor
    -1.75
     increa
    -1.73
     perfet
    -1.64
     secon
    -1.64
     depic
    -1.64
     inev
    -1.61
     Intere
    -1.60
     reluct
    -1.60
     scrat
    -1.57
     squa
    -1.57
    POSITIVE LOGITS
     are
    0.87
     were
    0.74
     themselves
    0.73
     aren
    0.73
     exist
    0.69
    AreEqual
    0.67
     هستند
    0.67
    are
    0.66
    postmedia
    0.63
     their
    0.62
    Activations Density 0.393%

    No Known Activations