© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3823
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or activities involving nudity

    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
    390
    +0.16
    0.6%
    1637
    +0.14
    0.5%
    1482
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.16
    0.03
    1637
    +0.14
    0.03
    812
    +0.14
    0.02
    Negative Logits
    Limiter
    -0.58
    Toaster
    -0.54
    Mover
    -0.52
     disques
    -0.51
    Tab
    -0.48
    Manger
    -0.48
    Fails
    -0.47
    Cleaner
    -0.47
    Addon
    -0.47
    Libr
    -0.46
    POSITIVE LOGITS
     involve
    0.98
     involving
    0.96
     INVOL
    0.95
     INVOLVED
    0.90
     involves
    0.85
     involvement
    0.81
     invol
    0.78
     Involvement
    0.77
     Involved
    0.76
    involved
    0.75
    Activations Density 0.080%

    No Known Activations