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. 6-RES-JB
    6. 6078
    Prev
    Next
    INDEX
    Explanations

    instances of the word "echo" or related concepts like repetition and reverberation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1045
    +0.14
    0.6%
    1604
    +0.13
    0.5%
    938
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.05
    690
    +0.13
    0.04
    1045
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.79
    XtraGrid
    -0.80
    HasColumnType
    -0.75
    disposing
    -0.75
    UnitTesting
    -0.69
    InputTagHelper
    -0.69
    ībā
    -0.69
     intptr
    -0.68
    ThemeOverlay
    -0.67
     државе
    -0.66
    POSITIVE LOGITS
     reluct
    1.90
     snoopy
    1.83
     disreg
    1.79
     ecru
    1.78
     impra
    1.78
     hairc
    1.77
     impractica
    1.76
     increa
    1.76
     cushi
    1.74
     affor
    1.74
    Activations Density 0.498%

    No Known Activations