© 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. 3564
    Prev
    Next
    INDEX
    Explanations

    temporal and discursive cues

    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
    1577
    +0.22
    0.8%
    674
    +0.21
    0.7%
    856
    +0.20
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1224
    +0.22
    0.07
    928
    +0.21
    0.01
    1577
    +0.20
    0.08
    Negative Logits
    Și
    -0.56
    Producción
    -0.55
    muito
    -0.51
    Aplicaciones
    -0.51
    melhor
    -0.51
    Ilustra
    -0.50
    Tecnologia
    -0.49
    printStats
    -0.48
    Psico
    -0.48
     Ceux
    -0.48
    POSITIVE LOGITS
    bewerken
    0.69
    <bos>
    0.66
    WriteTagHelper
    0.60
    ContentAsync
    0.59
     <>",
    0.56
    ))))))))
    0.55
    )))))
    0.53
     tranquillo
    0.53
     provato
    0.52
    "]]
    0.51
    Activations Density 1.026%

    No Known Activations