© 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. 629
    Prev
    Next
    INDEX
    Explanations

    introspective statements about personal feelings or perceptions

    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
    +0.27
    0.9%
    1967
    +0.10
    0.3%
    814
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1419
    +0.27
    0.04
    875
    +0.10
    0.03
    1761
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.84
     intersper
    -0.81
     disbur
    -0.68
     shenan
    -0.66
     enshr
    -0.65
     vanqu
    -0.65
     banish
    -0.64
     amass
    -0.61
     overcrow
    -0.60
     dismant
    -0.59
    POSITIVE LOGITS
     Minang
    0.72
    Fitment
    0.71
    GYPT
    0.70
     soulign
    0.68
     paillettes
    0.68
     frambo
    0.68
     tricot
    0.67
     pylab
    0.67
    AMILTON
    0.65
     kebaya
    0.65
    Activations Density 0.291%

    No Known Activations