© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2066
    Prev
    Next
    INDEX
    Explanations

    mentions of specific stages or levels in video games

    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
    228
    +0.16
    0.6%
    1262
    +0.13
    0.6%
    1705
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1837
    +0.16
    0.03
    228
    +0.13
    0.03
    645
    +0.13
    0.03
    Negative Logits
    ThemeProvider
    -0.47
     Ottobre
    -0.45
    Emilio
    -0.44
    rimir
    -0.42
    ssent
    -0.41
     оригіналу
    -0.40
     আর
    -0.40
     nozze
    -0.40
    menuItem
    -0.39
    eut
    -0.39
    POSITIVE LOGITS
     STAGE
    1.26
     stage
    1.22
     Stage
    1.17
    stage
    1.16
    Stage
    1.13
    STAGE
    1.08
     Stages
    1.08
    stages
    1.07
     stages
    1.05
    Stages
    1.02
    Activations Density 0.068%

    No Known Activations