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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 14
    Prev
    Next
    INDEX
    Explanations

    negative descriptors associated with harmful or immoral actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.14
    0.6%
    468
    +0.11
    0.5%
    1350
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.14
    0.04
    468
    +0.11
    0.04
    1363
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.73
    HasColumnType
    -0.97
    ApiModelProperty
    -0.82
    CreateMap
    -0.79
    lateinit
    -0.76
    flex
    -0.76
    addComponent
    -0.76
    IsRequired
    -0.76
    AllowUser
    -0.76
     createState
    -0.75
    POSITIVE LOGITS
     napoli
    1.86
     Minang
    1.82
     frankfurt
    1.81
     Juf
    1.77
     stockholm
    1.73
     bandung
    1.71
     ecru
    1.70
     milano
    1.68
     toledo
    1.67
     tramont
    1.67
    Activations Density 0.206%

    No Known Activations