© 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. 3787
    Prev
    Next
    INDEX
    Explanations

    sports-related information

    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
    1213
    +0.09
    0.3%
    1343
    +0.09
    0.3%
    1741
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1213
    +0.09
    0.05
    613
    +0.09
    0.05
    803
    +0.09
    0.04
    Negative Logits
    WithMany
    -0.57
    Vielleicht
    -0.52
    ContentAlignment
    -0.52
     ascorbic
    -0.52
     osmotic
    -0.52
     незавершена
    -0.51
     bromine
    -0.50
     propOrder
    -0.50
     tetrach
    -0.47
    phosph
    -0.47
    POSITIVE LOGITS
     Juf
    0.89
     Keny
    0.87
     Kün
    0.86
     Bartholo
    0.85
     Abbé
    0.83
     Departement
    0.83
     Pfal
    0.80
     tew
    0.80
     Ferdin
    0.77
     mikrofon
    0.76
    Activations Density 0.240%

    No Known Activations