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. 15558
    Prev
    Next
    INDEX
    Explanations

    phrases related to playing games or participating in political activities

    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
    1618
    +0.14
    0.5%
    1124
    +0.13
    0.4%
    1133
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1618
    +0.14
    0.05
    1124
    +0.13
    0.06
    1778
    +0.11
    0.05
    Negative Logits
     karbon
    -0.57
     vokal
    -0.51
     plastik
    -0.49
    ConstraintSet
    -0.48
    ("")]
    
    -0.47
     mikrofon
    -0.47
    mientos
    -0.47
     infrastruktur
    -0.47
    Caratteristiche
    -0.47
    AllowAnonymous
    -0.47
    POSITIVE LOGITS
     play
    1.14
     playing
    1.08
     PLAYING
    1.06
     PLAY
    1.05
     played
    1.03
     plays
    1.02
    play
    0.99
    playing
    0.98
     Play
    0.96
     Playing
    0.96
    Activations Density 0.145%

    No Known Activations