© 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. 3371
    Prev
    Next
    INDEX
    Explanations

    questions or reflections on societal issues or controversies

    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
    201
    +0.10
    0.3%
    971
    +0.10
    0.3%
    1601
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1601
    +0.10
    0.03
    201
    +0.10
    0.02
    220
    +0.10
    0.02
    Negative Logits
     Okt
    -0.54
     progressivement
    -0.54
    sä
    -0.51
     kompak
    -0.51
     protokol
    -0.51
     Boch
    -0.50
    kiv
    -0.50
     cil
    -0.49
     nécessairement
    -0.49
     effectivement
    -0.48
    POSITIVE LOGITS
     wonder
    1.06
     wondered
    1.04
     wondering
    0.97
     Wonder
    0.93
    wonder
    0.87
    Wonder
    0.87
     wonders
    0.86
     WONDER
    0.82
     wandered
    0.72
     Wonders
    0.72
    Activations Density 0.064%

    No Known Activations