© 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. 14189
    Prev
    Next
    INDEX
    Explanations

    code snippets related to a specific programming concept

    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
    +0.27
    0.8%
    872
    +0.17
    0.5%
    1150
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.27
    0.00
    872
    +0.17
    0.05
    1511
    +0.12
    0.01
    Negative Logits
    Desen
    -0.75
    Artigo
    -0.74
    Eksteraj
    -0.73
    Pró
    -0.73
    Siga
    -0.72
    Filmo
    -0.71
    Disciplina
    -0.69
    Televis
    -0.68
    Читати
    -0.67
    Desta
    -0.67
    POSITIVE LOGITS
     increa
    2.04
     guarante
    1.98
     scrat
    1.95
     maneu
    1.93
     encomp
    1.91
     suscep
    1.86
     perfet
    1.85
     inev
    1.84
     effe
    1.84
     overla
    1.84
    Activations Density 0.266%

    No Known Activations