© 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. 14655
    Prev
    Next
    INDEX
    Explanations

    information related to corporate sustainability initiatives and environmental impact reduction efforts

    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
    1978
    +0.14
    0.4%
    478
    +0.12
    0.3%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.14
    0.02
    371
    +0.12
    0.02
    1467
    +0.10
    0.02
    Negative Logits
     unspeak
    -1.13
     impractica
    -0.96
     tolerably
    -0.95
     impra
    -0.91
     vicissitudes
    -0.90
     unwarran
    -0.88
     philosophic
    -0.88
     vainly
    -0.88
     caprice
    -0.88
     sophistic
    -0.83
    POSITIVE LOGITS
     elek
    1.47
     utop
    1.47
     alkoh
    1.42
     makro
    1.39
     kask
    1.32
     silikon
    1.30
     kosme
    1.29
     plak
    1.27
     maske
    1.27
     maksi
    1.27
    Activations Density 0.051%

    No Known Activations