© 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. 7685
    Prev
    Next
    INDEX
    Explanations

    information related to family relationships and personal backgrounds

    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
    509
    +0.16
    0.5%
    1533
    +0.13
    0.4%
    223
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.16
    0.08
    1533
    +0.13
    0.03
    1081
    +0.10
    0.06
    Negative Logits
     makro
    -0.96
     saar
    -0.95
     traktor
    -0.94
     kram
    -0.93
     ohr
    -0.93
     kasa
    -0.91
     eko
    -0.91
     kask
    -0.90
     kug
    -0.90
     siena
    -0.88
    POSITIVE LOGITS
     father
    0.95
     dad
    0.94
     parents
    0.93
    <bos>
    0.93
     siblings
    0.86
     parent
    0.86
     Dad
    0.84
     parental
    0.83
     family
    0.82
     mom
    0.79
    Activations Density 0.569%

    No Known Activations