© 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. 3538
    Prev
    Next
    INDEX
    Explanations

    references to the company Sony as well as technical terms and product names related to technology

    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
    1741
    +0.15
    0.5%
    1177
    +0.14
    0.5%
    1984
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.15
    0.04
    1177
    +0.14
    0.03
    1798
    +0.12
    0.04
    Negative Logits
     chiaramente
    -0.57
     xdrive
    -0.54
     picha
    -0.53
     ktm
    -0.53
    thinkable
    -0.52
    mistak
    -0.52
    relenting
    -0.52
     liberality
    -0.51
     updateTime
    -0.50
    wavering
    -0.50
    POSITIVE LOGITS
     Sony
    0.86
    Sony
    0.80
     Godt
    0.71
     sony
    0.62
    sony
    0.60
    espół
    0.58
    estaw
    0.57
     stoff
    0.57
     Strukt
    0.53
     Développement
    0.53
    Activations Density 0.145%

    No Known Activations