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. 6756
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that indicate radical change or ideas

    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
    1.2%
    161
    +0.14
    0.8%
    871
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.23
    0.02
    1351
    +0.14
    0.02
    871
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.82
     serve
    -0.71
    public
    -0.69
    put
    -0.68
     put
    -0.68
     get
    -0.68
     earn
    -0.65
     let
    -0.64
     manage
    -0.64
    ⓧ
    -0.63
    POSITIVE LOGITS
     Minang
    1.51
     santiago
    1.46
     riva
    1.38
     Juf
    1.37
     milano
    1.37
     ftu
    1.35
     frankfurt
    1.35
     bandung
    1.35
     hcm
    1.35
     stockholm
    1.34
    Activations Density 0.034%

    No Known Activations