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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14335
    Prev
    Next
    INDEX
    Explanations

    information about sports schedules and matchups

    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
    604
    +0.11
    0.4%
    674
    +0.09
    0.3%
    998
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.11
    0.03
    175
    +0.09
    0.03
    693
    +0.08
    0.02
    Negative Logits
     unspeak
    -1.20
     intersper
    -1.19
     shenan
    -1.15
     disagre
    -1.10
     apprehen
    -1.10
     Confu
    -1.07
     reluct
    -1.06
     Juf
    -1.05
     depic
    -1.03
     encomp
    -1.03
    POSITIVE LOGITS
    Бахар
    0.53
     bezeichneter
    0.52
    GEBURTSDATUM
    0.50
     doPost
    0.50
    autoreleasepool
    0.49
     שוליים
    0.49
    تقاوى
    0.49
     Roskov
    0.48
    homonymie
    0.48
    Enllaços
    0.48
    Activations Density 0.257%

    No Known Activations