© 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. 976
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activities and justice

    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
    481
    +0.13
    0.5%
    468
    +0.12
    0.5%
    1828
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.13
    0.03
    1828
    +0.12
    0.03
    468
    +0.12
    0.03
    Negative Logits
     ricordare
    -0.55
    ultuous
    -0.54
    rijfs
    -0.52
     vogliamo
    -0.52
     AssemblyProduct
    -0.51
     podjet
    -0.51
     ricorda
    -0.51
     facciamo
    -0.50
     Spirito
    -0.50
    ceğini
    -0.49
    POSITIVE LOGITS
     crime
    1.32
    Crime
    1.20
     Crime
    1.19
    crime
    1.17
     crimes
    1.10
     CRIME
    1.01
     Crimes
    1.00
    crimes
    0.91
     Crim
    0.80
     Crimin
    0.75
    Activations Density 0.076%

    No Known Activations