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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8326
    Prev
    Next
    INDEX
    Explanations

    references to specific company names or product names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    283
    +0.13
    0.4%
    1741
    +0.13
    0.4%
    304
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.13
    0.06
    227
    +0.13
    0.07
    283
    +0.11
    0.01
    Negative Logits
     shewn
    -0.84
    Datuak
    -0.82
     különböz
    -0.73
     blest
    -0.70
    WriteBarrier
    -0.65
    SPECTION
    -0.63
     hozz
    -0.63
     friable
    -0.62
     besz
    -0.62
     szüks
    -0.61
    POSITIVE LOGITS
     gesta
    1.25
     Nö
    1.24
     frau
    1.23
     plak
    1.23
     utop
    1.20
     glan
    1.20
     drap
    1.20
     elek
    1.18
     logis
    1.17
     biograf
    1.16
    Activations Density 0.339%

    No Known Activations