© 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. 583
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of boasting or highlighting features

    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
    +0.20
    0.7%
    1056
    +0.07
    0.2%
    1910
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    731
    +0.20
    0.05
    681
    +0.07
    0.04
    677
    +0.06
    0.04
    Negative Logits
    <bos>
    -3.38
    ,
    -1.08
    /
    -1.01
    .
    -0.99
    :
    -0.96
    public
    -0.95
    ;
    -0.94
     (
    -0.93
    (
    -0.93
     im
    -0.91
    POSITIVE LOGITS
     increa
    3.42
     affor
    3.28
     inev
    3.23
     disagre
    3.19
     emphat
    3.14
     strick
    3.13
     impra
    3.13
     maneu
    3.10
     ?...
    3.09
     reluct
    3.08
    Activations Density 0.394%

    No Known Activations