© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 572
    Prev
    Next
    INDEX
    Explanations

    instances of the word "computer" or related terms

    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
    +0.26
    1.5%
    1103
    +0.12
    0.7%
    204
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    689
    +0.26
    0.03
    1103
    +0.12
    0.03
    204
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.68
    ⓧ
    -0.80
     mobilize
    -0.74
    <?
    -0.74
     intersper
    -0.70
     amass
    -0.70
     endow
    -0.70
     consolidate
    -0.68
    /**
    -0.67
     defray
    -0.67
    POSITIVE LOGITS
     bandung
    1.33
     jawa
    1.18
     computer
    1.17
     nuoc
    1.16
     lele
    1.15
     Jambi
    1.15
     Palembang
    1.15
     Computer
    1.14
    Computer
    1.13
     saar
    1.13
    Activations Density 0.034%

    No Known Activations