© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 626
    Prev
    Next
    INDEX
    Explanations

    terms related to character development and authenticity

    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
    +0.30
    1.2%
    764
    +0.13
    0.5%
    184
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.30
    0.05
    253
    +0.13
    0.06
    1473
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.20
    
    -0.94
    /***
    -0.93
    /**
    -0.83
     inaugurate
    -0.80
    ⓧ
    -0.80
     evacuate
    -0.74
     incarcer
    -0.74
     disbur
    -0.74
     intersper
    -0.74
    POSITIVE LOGITS
     paradiso
    0.71
     pageNo
    0.71
     ados
    0.69
     geniales
    0.69
     bandung
    0.69
    tawan
    0.67
     marea
    0.67
     frambo
    0.67
     saad
    0.67
     ferie
    0.66
    Activations Density 1.052%

    No Known Activations