Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1187
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "back" and related phrases indicating a historical reference or context

    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
    +0.23
    1.1%
    101
    +0.12
    0.6%
    1256
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.23
    0.05
    559
    +0.12
    0.05
    663
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.51
    /***
    
    -0.76
    ⓧ
    -0.67
    <?
    -0.65
    createComponent
    -0.60
    /*++
    -0.59
    },[])
    -0.59
    MockBean
    -0.58
    //{
    
    -0.56
    Tracce
    -0.55
    POSITIVE LOGITS
     practition
    1.30
     unwarran
    1.27
     pamph
    1.26
     disagre
    1.23
     stockholm
    1.19
     Backman
    1.17
     unlaw
    1.16
     Minang
    1.16
     Juf
    1.15
     philanth
    1.14
    Activations Density 0.070%

    No Known Activations