© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11208
    Prev
    Next
    INDEX
    Explanations

    key details in news articles regarding criminal incidents and legal proceedings

    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
    1150
    +0.10
    0.3%
    1055
    +0.09
    0.3%
    136
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1055
    +0.10
    0.05
    1693
    +0.09
    0.04
    1784
    +0.08
    0.04
    Negative Logits
     effe
    -1.54
     ?...
    -1.50
     increa
    -1.44
     desir
    -1.42
     emphat
    -1.41
     aen
    -1.38
     !...
    -1.34
     accla
    -1.34
     inconce
    -1.33
     nece
    -1.32
    POSITIVE LOGITS
     yet
    0.89
     but
    0.80
    存于互联网档案馆
    0.78
     nor
    0.77
    yet
    0.75
     snippetHide
    0.74
    StoryboardSegue
    0.72
    but
    0.72
     gawas
    0.71
     nhưng
    0.68
    Activations Density 0.204%

    No Known Activations