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. 6165
    Prev
    Next
    INDEX
    Explanations

    cryptographic terms or identifiers

    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
    •Steering
    fun feature

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.27
    1.2%
    876
    +0.26
    1.2%
    1499
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.27
    -0.03
    1499
    +0.26
    0.12
    283
    +0.15
    -0.01
    Negative Logits
    <bos>
    -2.35
     at
    -0.96
     put
    -0.95
     let
    -0.94
     don
    -0.93
     had
    -0.92
     so
    -0.92
     once
    -0.91
    ,
    -0.90
     now
    -0.90
    POSITIVE LOGITS
     effe
    3.75
     increa
    3.62
     affor
    3.51
     guarante
    3.48
     desir
    3.44
     maneu
    3.44
     wien
    3.41
     aen
    3.36
     inev
    3.33
     thut
    3.31
    Activations Density 1.519%

    No Known Activations