Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13362
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific concepts and technology, particularly related to space travel and understanding the universe

    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
    1485
    +0.13
    0.4%
    944
    +0.10
    0.3%
    1356
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1485
    +0.13
    0.03
    944
    +0.10
    0.03
    191
    +0.09
    0.03
    Negative Logits
    político
    -0.61
     typelib
    -0.59
     esboço
    -0.54
     للاسماء
    -0.53
     praktik
    -0.52
     censiti
    -0.52
    IMPORTED
    -0.51
     parteci
    -0.51
    Билгалдахарш
    -0.50
    ContentAsync
    -0.50
    POSITIVE LOGITS
     speeds
    1.16
     speed
    1.13
     velocities
    1.00
     velocity
    0.96
    speed
    0.92
    Speed
    0.87
     Speed
    0.86
     Speeds
    0.83
     speeding
    0.81
     SPEED
    0.76
    Activations Density 0.304%

    No Known Activations