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. 2980
    Prev
    Next
    INDEX
    Explanations

    technical descriptions including mention of technical specifications, dual-channel functionality, and processing units

    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
    897
    +0.13
    0.5%
    1870
    +0.13
    0.5%
    90
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.13
    0.02
    1328
    +0.13
    0.02
    143
    +0.12
    0.02
    Negative Logits
    رشف
    -0.45
     bulunabilir
    -0.45
     ElementRef
    -0.42
     TType
    -0.41
    梗
    -0.40
    Shirts
    -0.40
    chiff
    -0.39
    inence
    -0.39
    볍
    -0.39
     Camp
    -0.39
    POSITIVE LOGITS
    Dual
    1.12
     Dual
    1.07
     dual
    1.07
    dual
    0.99
     DUAL
    0.93
     pymysql
    0.91
     twin
    0.86
     alberto
    0.80
     conftest
    0.79
    twin
    0.77
    Activations Density 0.071%

    No Known Activations