© 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. 581
    Prev
    Next
    INDEX
    Explanations

    terms related to observation and advisory roles

    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
    1870
    +0.20
    0.7%
    50
    +0.18
    0.7%
    678
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.20
    0.08
    1385
    +0.18
    0.08
    678
    +0.12
    0.07
    Negative Logits
    <bos>
    -2.50
    HasColumnType
    -0.78
    <!--
    -0.74
     ***!
    -0.73
    DropColumn
    -0.70
    principalColumn
    -0.70
    RemoveField
    -0.68
    CrossOrigin
    -0.65
    RTDA
    -0.65
     invokingState
    -0.64
    POSITIVE LOGITS
     thut
    1.39
     aen
    1.34
     emphat
    1.33
     fta
    1.31
     ftu
    1.29
     feen
    1.26
     nomine
    1.24
     mef
    1.22
     §.
    1.22
     perfon
    1.21
    Activations Density 0.675%

    No Known Activations