© 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. 2540
    Prev
    Next
    INDEX
    Explanations

    information related to specific entities and activities within a context of discussion

    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
    1842
    +0.13
    0.4%
    1870
    +0.12
    0.4%
    50
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.13
    0.05
    1870
    +0.12
    0.06
    227
    +0.12
    0.10
    Negative Logits
     biograf
    -0.56
    ganu
    -0.52
     otomatig
    -0.52
    Inggris
    -0.51
     antemano
    -0.51
     Winaray
    -0.51
     minimalis
    -0.49
    astéro
    -0.49
     sumpay
    -0.49
    PerformLayout
    -0.49
    POSITIVE LOGITS
     maneu
    1.37
     depic
    1.31
     shenan
    1.21
     increa
    1.14
     inev
    1.13
     encomp
    1.12
     disreg
    1.11
     uninten
    1.10
     berea
    1.09
     reluct
    1.09
    Activations Density 1.363%

    No Known Activations