© 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. 14624
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts

    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
    1343
    +0.09
    0.2%
    1618
    +0.08
    0.2%
    134
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.09
    0.04
    1087
    +0.08
    0.02
    704
    +0.08
    0.01
    Negative Logits
     reluct
    -1.12
     inev
    -1.10
     resear
    -1.08
     suscep
    -1.08
     compen
    -1.07
     inconce
    -1.07
     increa
    -1.06
     depic
    -1.04
     laun
    -1.03
     accla
    -1.03
    POSITIVE LOGITS
     downright
    0.67
     outright
    0.65
     sogar
    0.62
     necessarily
    0.57
    eniably
    0.56
     exceeding
    0.55
     ElevatedButton
    0.54
    USTAIN
    0.52
    甚至是
    0.51
     InkWell
    0.51
    Activations Density 0.178%

    No Known Activations