© 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. 12933
    Prev
    Next
    INDEX
    Explanations

    brain regions and responses related to inflammation and pain

    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
    876
    +0.18
    0.6%
    1499
    +0.18
    0.6%
    283
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.18
    0.08
    736
    +0.18
    0.05
    690
    +0.17
    0.03
    Negative Logits
     Juventud
    -0.92
     Olimpia
    -0.81
     Belén
    -0.75
     tortas
    -0.75
     Compañ
    -0.74
     Asunción
    -0.74
     parteci
    -0.73
     Darío
    -0.73
     Hogar
    -0.73
     Depor
    -0.73
    POSITIVE LOGITS
     disagre
    1.33
     perfon
    1.25
     ftu
    1.24
     apprehen
    1.23
     fup
    1.22
     reconno
    1.22
     shewn
    1.20
     guarante
    1.20
     effe
    1.19
     feen
    1.19
    Activations Density 0.293%

    No Known Activations