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. 134
    Prev
    Next
    INDEX
    Explanations

    information related to renewable energy projects and data control architecture

    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
    1343
    +0.13
    0.4%
    876
    +0.12
    0.4%
    304
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1843
    +0.13
    0.04
    1043
    +0.12
    0.04
    678
    +0.12
    0.04
    Negative Logits
    ACKNOWLEDG
    -0.81
     그의
    -0.79
    Quién
    -0.77
     חיצוני
    -0.76
    Grüße
    -0.76
    Beberapa
    -0.76
     그것
    -0.75
    Secara
    -0.72
    Setiap
    -0.72
    Imagem
    -0.72
    POSITIVE LOGITS
     socie
    2.15
     embra
    2.04
     milano
    1.98
     igno
    1.98
     casio
    1.97
     dispen
    1.96
     pixabay
    1.95
     pessi
    1.93
     dises
    1.92
     emble
    1.92
    Activations Density 0.149%

    No Known Activations